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
    .de
    -0.07
     "%
    -0.06
    %"
    -0.06
    ً
    -0.06
     bc
    -0.06
     generator
    -0.06
    極
    -0.06
     lô
    -0.06
     lado
    -0.06
    頻
    -0.06
    POSITIVE LOGITS
    екс
    0.07
    getState
    0.07
    Permanent
    0.07
    bits
    0.06
     Apost
    0.06
    itious
    0.06
     Buccane
    0.06
     mamma
    0.06
     paramInt
    0.06
    _MOD
    0.06
    Act Density 0.140%

    No Known Activations