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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -depend
    -0.07
    []{
    -0.07
    (asset
    -0.07
     Musical
    -0.07
    _no
    -0.07
    Deep
    -0.07
    -brand
    -0.07
     lied
    -0.06
     canc
    -0.06
     маст
    -0.06
    POSITIVE LOGITS
    RING
    0.06
    _UFunction
    0.06
    duğ
    0.06
    dictions
    0.06
    VES
    0.06
    цуз
    0.06
    _resolve
    0.06
    чины
    0.06
    HexString
    0.06
     účin
    0.06
    Act Density 0.000%

    No Known Activations