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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Az
    -0.07
    .metadata
    -0.07
    CDC
    -0.06
    ｊ
    -0.06
    stein
    -0.06
    ｯ
    -0.06
    ソン
    -0.06
    _Util
    -0.06
    plane
    -0.06
    になる
    -0.06
    POSITIVE LOGITS
     suspect
    0.06
    errorCode
    0.06
    دواج
    0.06
    (logits
    0.06
    ................................................................
    0.06
     UINT
    0.06
    -monitor
    0.06
    (single
    0.06
    (find
    0.05
     ignores
    0.05
    Act Density 0.019%

    No Known Activations