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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     специфи
    0.44
     вій
    0.42
    AssignableFrom
    0.42
    ]`
    0.42
     እንኳ
    0.41
    似的
    0.40
    ピュー
    0.39
    Specific
    0.39
    -
    0.39
    雌
    0.39
    POSITIVE LOGITS
     Ikea
    0.50
     pasar
    0.47
     reorgan
    0.46
     大阪
    0.45
     नीट
    0.43
    菻
    0.42
     tirar
    0.42
     jeżeli
    0.42
     tumb
    0.41
    .,"
    0.41
    Act Density 0.000%

    No Known Activations