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

    Neuronpedia

    INDEX
    Explanations

    calculations and formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Collision
    -0.08
    tí
    -0.06
    σει
    -0.06
    spacing
    -0.06
    IGNORE
    -0.06
     Suicide
    -0.06
     Diploma
    -0.06
     incidental
    -0.06
     Fiction
    -0.06
    .notify
    -0.06
    POSITIVE LOGITS
    MethodManager
    0.08
     pledged
    0.06
     Obr
    0.06
     Chatt
    0.06
     togg
    0.06
     Αν
    0.06
     İşte
    0.06
    'order
    0.06
    _references
    0.06
     lưu
    0.06
    Act Density 0.025%

    No Known Activations