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

    Neuronpedia

    INDEX
    Explanations

    Basic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    焦
    -0.07
     handle
    -0.07
     מל
    -0.07
    转身
    -0.07
     لأ
    -0.07
    ируется
    -0.07
    녘
    -0.06
     فأ
    -0.06
     ⓘ
    -0.06
    .BUTTON
    -0.06
    POSITIVE LOGITS
     prueba
    0.08
    Strict
    0.08
    QUARE
    0.08
     recruits
    0.07
     drastic
    0.07
    _subtitle
    0.07
     Cruz
    0.07
     kişinin
    0.07
    Cool
    0.07
    _corr
    0.07
    Act Density 0.004%

    No Known Activations