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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and names related to individuals or fictional characters

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

    Kuete et al

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     spilled
    -0.45
     nakalista
    -0.45
     floor
    -0.43
     slipping
    -0.41
    alinga
    -0.41
    页面存档备份
    -0.40
     padding
    -0.40
     Muk
    -0.40
    expandindo
    -0.40
     visualization
    -0.39
    POSITIVE LOGITS
    новништво
    0.75
     enfans
    0.63
    AddTagHelper
    0.63
     ainfi
    0.63
    principalColumn
    0.60
    pulseira
    0.55
    InputTagHelper
    0.55
    ientras
    0.55
     aguja
    0.54
    jenigen
    0.54
    Act Density 0.243%

    No Known Activations