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

    Neuronpedia

    INDEX
    Explanations

    small

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     EU
    -0.07
    rules
    -0.07
     annotate
    -0.07
     Waste
    -0.07
     Mat
    -0.07
    Math
    -0.07
    椋
    -0.07
     Bulls
    -0.07
     JTextField
    -0.07
     CONCAT
    -0.07
    POSITIVE LOGITS
    _serializer
    0.07
     subdivision
    0.07
    mpr
    0.06
     censor
    0.06
     timeStamp
    0.06
    始终坚持
    0.06
    ณ
    0.06
    ahl
    0.06
    している
    0.06
    stras
    0.06
    Act Density 0.015%

    No Known Activations