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

    Neuronpedia

    INDEX
    Explanations

    package

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    褲
    -0.07
    ux
    -0.06
    ês
    -0.06
    _SB
    -0.06
    (Bundle
    -0.06
    ucht
    -0.06
    xBF
    -0.06
    _am
    -0.06
     Gab
    -0.06
     agua
    -0.06
    POSITIVE LOGITS
     Sept
    0.07
    目的是
    0.07
     campaign
    0.07
     opposing
    0.07
     сез
    0.06
     opposite
    0.06
     modern
    0.06
    ספטמ
    0.06
     titled
    0.06
     trabajo
    0.06
    Act Density 0.001%

    No Known Activations