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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to authors or contributors in an academic context

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

    before citations or names

    np_acts-logits-general · gemini-2.0-flash

    multilingual character sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    avice
    -0.54
    onesi
    -0.52
     come
    -0.52
     Ba
    -0.52
    zke
    -0.51
    vermögen
    -0.50
     ri
    -0.50
    acki
    -0.50
     sao
    -0.49
    manni
    -0.49
    POSITIVE LOGITS
    HasAnnotation
    0.78
     Italijani
    0.77
    SharedDtor
    0.72
    脚注の使い方
    0.68
     DMD
    0.68
     useStyles
    0.67
     PicClick
    0.66
    outSlope
    0.65
    ItemBackground
    0.65
     تضيفلها
    0.65
    Act Density 0.292%

    No Known Activations