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

    Neuronpedia

    INDEX
    Explanations

    parameter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    HX
    -0.07
    eeper
    -0.07
    american
    -0.06
    也有
    -0.06
    cích
    -0.06
    kernel
    -0.06
     sap
    -0.06
    fig
    -0.06
     вимог
    -0.06
     enters
    -0.06
    POSITIVE LOGITS
    号
    0.06
     二
    0.06
    모
    0.06
     predecess
    0.06
    �
    0.06
     skinny
    0.06
    _article
    0.06
     rains
    0.06
    (filePath
    0.05
    abis
    0.05
    Act Density 0.004%

    No Known Activations