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

    Neuronpedia

    INDEX
    Explanations

    math expressions

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mand
    -0.07
    woord
    -0.06
     kole
    -0.06
    каÑĢ
    -0.06
    .Messaging
    -0.06
     kancel
    -0.06
    æ¨
    -0.06
    urg
    -0.06
    виÑĩай
    -0.06
    oust
    -0.06
    POSITIVE LOGITS
    s
    0.11
    a
    0.08
    .
    0.08
    e
    0.07
    adays
    0.07
    ï¸ı
    0.07
    z
    0.07
    ://
    0.07
    oriously
    0.07
    onya
    0.07
    Act Density 0.075%

    No Known Activations