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

    Neuronpedia

    INDEX
    Explanations

    dismissal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ő
    -0.08
     đèn
    -0.07
     PARTIC
    -0.07
     tarn
    -0.07
    _O
    -0.07
    .Ph
    -0.07
    �
    -0.07
     torpedo
    -0.07
    动作
    -0.07
    瞀
    -0.07
    POSITIVE LOGITS
     encounters
    0.07
    yp
    0.07
    .when
    0.07
    د
    0.06
    访
    0.06
    _FOR
    0.06
    ием
    0.06
    فير
    0.06
    ib
    0.06
     reopened
    0.06
    Act Density 0.004%

    No Known Activations