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

    Neuronpedia

    INDEX
    Explanations

    writing/rewriting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tournament
    -0.07
    abez
    -0.07
    crest
    -0.06
    gow
    -0.06
     zw
    -0.06
     authService
    -0.06
     Elon
    -0.06
    .rnn
    -0.06
    bugs
    -0.06
     pool
    -0.06
    POSITIVE LOGITS
     MLA
    0.07
     analyst
    0.06
    ेत
    0.06
    Buy
    0.06
     Efficient
    0.06
    642
    0.06
     này
    0.06
     고
    0.06
    их
    0.06
    共同
    0.06
    Act Density 0.170%

    No Known Activations