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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .consume
    -0.07
    implementation
    -0.06
     stemmed
    -0.06
     Gods
    -0.06
     爱
    -0.06
     Thief
    -0.06
     Jump
    -0.06
     nhiễm
    -0.06
    _oper
    -0.06
     zar
    -0.06
    POSITIVE LOGITS
    /terms
    0.07
     TRAIN
    0.07
    普
    0.06
    ailer
    0.06
    angled
    0.06
     Resist
    0.06
    ②
    0.06
    \">↵
    0.06
     insider
    0.06
    .digital
    0.06
    Act Density 0.043%

    No Known Activations