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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to changes, developments, and implementations in a structured context

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

    Fractions and ratios

    np_acts-logits-general · gemini-2.0-flash

    numerical computation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     appunto
    -1.06
     justement
    -0.77
    Datuak
    -0.73
     justamente
    -0.72
     متعلقه
    -0.72
     própri
    -0.71
    それも
    -0.70
     accordingly
    -0.69
     właśnie
    -0.66
     dunque
    -0.66
    POSITIVE LOGITS
    ]--;
    0.58
    thoven
    0.55
    intenance
    0.54
    0.52
    licopter
    0.50
    AllAfrica
    0.49
    ffix
    0.49
    BRUARY
    0.48
    ilingual
    0.48
     Braille
    0.48
    Act Density 1.528%

    No Known Activations