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

    Neuronpedia

    INDEX
    Explanations

    words related to probabilities and deductive reasoning

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ī´
    -0.07
    ULLET
    -0.06
    formace
    -0.06
    orney
    -0.06
    sted
    -0.06
    .Callback
    -0.06
    ptime
    -0.06
    aped
    -0.06
    Æł
    -0.06
    annis
    -0.06
    POSITIVE LOGITS
     majority
    0.19
     minority
    0.12
     Majority
    0.12
     numerical
    0.10
     mayorÃŃa
    0.10
     votes
    0.10
     numer
    0.10
     outnumber
    0.09
     numbers
    0.09
    numer
    0.09
    Act Density 0.064%

    No Known Activations