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

    Neuronpedia

    INDEX
    Explanations

    research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     det
    -0.06
    ToDelete
    -0.06
    tor
    -0.06
    _tokenize
    -0.06
     mg
    -0.06
     Jew
    -0.06
    \Id
    -0.06
     AQ
    -0.06
     multiprocessing
    -0.06
     getter
    -0.06
    POSITIVE LOGITS
     Moving
    0.06
    801
    0.06
    럽
    0.06
    .AUTH
    0.06
     nedost
    0.06
    lásil
    0.06
     Include
    0.06
     accomplishment
    0.06
     इन
    0.06
     units
    0.06
    Act Density 0.055%

    No Known Activations