Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to significant accomplishments or milestones metaphorically described as "miracles."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    amazement or rare occurrences

    np_acts-logits-general · gemini-2.0-flash

    extraordinary achievements and events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Бахар
    -0.64
    WriteBarrier
    -0.60
    bootstrapcdn
    -0.58
     initComponents
    -0.57
    houettes
    -0.53
     "..\..\
    -0.53
     exacerb
    -0.52
    Sesion
    -0.50
    )=-\
    -0.49
    ContentAlignment
    -0.49
    POSITIVE LOGITS
     miracle
    1.90
     miracles
    1.86
     miraculous
    1.81
     feats
    1.72
     feat
    1.63
    miracle
    1.55
     remarkable
    1.52
     marvels
    1.49
     Miracles
    1.48
     achievement
    1.42
    Act Density 0.234%

    No Known Activations