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

    Neuronpedia

    INDEX
    Explanations

    securities, Section, Exchange, holds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     umož
    0.44
    বেশ
    0.44
     bár
    0.40
     acceso
    0.40
    rédients
    0.40
    帽子
    0.39
     कॉस्ट
    0.38
     φύ
    0.38
    碜
    0.38
     공식
    0.37
    POSITIVE LOGITS
    curity
    0.44
    ign
    0.44
     Column
    0.42
     holds
    0.40
     ign
    0.40
    Exchange
    0.40
    holds
    0.40
     Exchange
    0.39
     column
    0.39
    column
    0.38
    Act Density 0.002%

    No Known Activations