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

    Neuronpedia

    INDEX
    Explanations

    y

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     venue
    -0.07
    เสน
    -0.07
     receiver
    -0.07
     covariance
    -0.07
    storage
    -0.07
    .Column
    -0.07
     thumbnails
    -0.07
     quelle
    -0.07
    Teachers
    -0.06
     Barg
    -0.06
    POSITIVE LOGITS
    amment
    0.06
    огу
    0.06
    ANTS
    0.06
    Wr
    0.06
    _apply
    0.06
    종
    0.06
    ulp
    0.06
    ��
    0.06
    "]]
    0.06
     distributions
    0.06
    Act Density 0.004%

    No Known Activations