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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    тий
    -0.07
     Refresh
    -0.07
     prefer
    -0.07
    .getTime
    -0.06
     jerk
    -0.06
     elé
    -0.06
     điện
    -0.06
    ieron
    -0.06
     hon
    -0.06
     Freund
    -0.06
    POSITIVE LOGITS
    Msp
    0.07
    15
    0.06
     проб
    0.06
     Spot
    0.06
     کشورهای
    0.06
    幅
    0.06
     sợ
    0.05
    13
    0.05
    TimeZone
    0.05
    codec
    0.05
    Act Density 0.002%

    No Known Activations