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

    Neuronpedia

    INDEX
    Explanations

    considered

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Within
    -0.07
    standing
    -0.07
    }_${
    -0.06
     Як
    -0.06
    chemas
    -0.06
    >Hello
    -0.06
    Better
    -0.06
    coholic
    -0.06
    "%
    -0.06
    (domain
    -0.06
    POSITIVE LOGITS
    olate
    0.07
     gái
    0.06
     ambush
    0.06
    نا
    0.06
     mutableListOf
    0.06
     pParent
    0.06
    _State
    0.06
     niż
    0.06
     Міністер
    0.06
    caffe
    0.06
    Act Density 0.011%

    No Known Activations