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

    Neuronpedia

    INDEX
    Explanations

    dump

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rumors
    -0.06
     guided
    -0.06
     pymongo
    -0.06
     Border
    -0.06
     diagonal
    -0.06
     pund
    -0.06
     neurons
    -0.06
     hypers
    -0.06
     мех
    -0.06
    라는
    -0.06
    POSITIVE LOGITS
     �
    0.07
    نگی
    0.07
    ayne
    0.07
     لب
    0.07
     Harden
    0.06
     ein
    0.06
    ぁ
    0.06
    lemen
    0.06
    od
    0.06
    <const
    0.06
    Act Density 0.002%

    No Known Activations