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

    Neuronpedia

    INDEX
    Explanations

    non-English

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fixed
    -0.07
    uchen
    -0.07
     tape
    -0.07
    itä
    -0.07
    chter
    -0.06
    .street
    -0.06
     plan
    -0.06
    grid
    -0.06
    タ
    -0.06
    /pdf
    -0.06
    POSITIVE LOGITS
     обязатель
    0.06
     Laugh
    0.06
     حتی
    0.06
    (':',
    0.06
    ้าย
    0.06
    .GetInt
    0.06
    漂
    0.06
    *>&
    0.06
    ।↵↵
    0.06
     đáp
    0.06
    Act Density 0.014%

    No Known Activations