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

    Neuronpedia

    INDEX
    Explanations

    words relating to mathematical and logical problem-solving

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     several
    -0.09
     Several
    -0.08
    udoku
    -0.07
    Several
    -0.07
     wherever
    -0.07
    cks
    -0.07
     Ulus
    -0.06
    íİ
    -0.06
    iston
    -0.06
    unsch
    -0.06
    POSITIVE LOGITS
     each
    0.14
     EACH
    0.10
    each
    0.10
     Each
    0.10
    Each
    0.10
    .each
    0.08
     má»Ĺi
    0.07
     whom
    0.07
     cada
    0.07
    ï¼Įæ¯ı
    0.07
    Act Density 0.157%

    No Known Activations