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

    Neuronpedia

    INDEX
    Explanations

    references to quantities, amounts, or measurements in the text

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

    Words/tokens followed by "recognized", "already", "that"

    np_acts-logits-general · gemini-2.0-flash

    concepts and their associated actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     дописавши
    -0.79
     елның
    -0.77
    wrote
    -0.66
    حياتها
    -0.65
     ſche
    -0.65
     يتيمه
    -0.64
     Wrote
    -0.64
     Hiring
    -0.63
     Wearing
    -0.63
     Resistant
    -0.63
    POSITIVE LOGITS
     put
    0.75
     being
    0.71
     set
    0.61
     that
    0.60
     taken
    0.59
     successfully
    0.54
     which
    0.54
     added
    0.54
     used
    0.53
     found
    0.52
    Act Density 0.842%

    No Known Activations