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

    Neuronpedia

    INDEX
    Explanations

    code and technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    یزات
    -0.07
    ınıza
    -0.06
    entries
    -0.06
    iced
    -0.06
     fool
    -0.06
    손
    -0.06
    imento
    -0.06
     cand
    -0.06
     женщин
    -0.06
    .EditText
    -0.05
    POSITIVE LOGITS
    sorted
    0.07
    Prof
    0.07
    ＿＿＿＿＿＿＿＿
    0.07
     reboot
    0.07
    273
    0.06
    _strlen
    0.06
     fem
    0.06
    ，或
    0.06
    Typ
    0.06
    过来
    0.06
    Act Density 0.000%

    No Known Activations