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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    getData
    -0.08
    uting
    -0.08
    😤
    -0.07
     nối
    -0.07
     plaster
    -0.07
     ost
    -0.07
    �
    -0.07
    售后
    -0.07
    وصل
    -0.07
    .Protocol
    -0.07
    POSITIVE LOGITS
     seriously
    0.07
    뻑
    0.07
    (QStringLiteral
    0.07
     whiskey
    0.06
     época
    0.06
     khảo
    0.06
     אחרות
    0.06
     deity
    0.06
     rais
    0.06
    就有
    0.06
    Act Density 0.000%

    No Known Activations