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

    Neuronpedia

    INDEX
    Explanations

    words related to software code and applying for exams

    oai_token-act-pair · gemini-2.0-flash

    Code and quiz related

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UnusedPrivate
    -0.55
    Jeografia
    -0.55
    oiseau
    -0.54
    Filmografia
    -0.52
     Italijani
    -0.52
    rrggbb
    -0.51
     الاطلاع
    -0.51
     ویکی‌پدی
    -0.50
    astéroïdes
    -0.50
     ویکی‌پدیا
    -0.50
    POSITIVE LOGITS
    atta
    0.53
    chach
    0.51
    extAlignment
    0.50
    msg
    0.49
    ÍST
    0.49
    telse
    0.49
    ingh
    0.48
    ableView
    0.48
    anum
    0.48
    flashdata
    0.47
    Act Density 24.492%

    No Known Activations