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

    Neuronpedia

    INDEX
    Explanations

    references to contributors and acknowledgments in academic texts

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

    Titles and names of people

    np_acts-logits-general · gemini-2.0-flash

    titled individual names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Offisielt
    -0.81
    исленность
    -0.78
     оригіналу
    -0.77
     BoxDecoration
    -0.75
     Joss
    -0.73
     HasFactory
    -0.73
    awtextra
    -0.72
     StatelessWidget
    -0.71
     greateſt
    -0.71
     ſche
    -0.70
    POSITIVE LOGITS
     K
    0.66
     David
    0.58
     John
    0.58
     Dr
    0.55
     $\
    0.54
     B
    0.54
     And
    0.54
     Man
    0.54
     L
    0.53
     Mark
    0.53
    Act Density 0.455%

    No Known Activations