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

    Neuronpedia

    INDEX
    Explanations

    off

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    カー
    -0.07
    dB
    -0.07
    WC
    -0.06
     bumped
    -0.06
    pirit
    -0.06
    =====
    -0.06
     duke
    -0.06
    ̆
    -0.06
     Его
    -0.06
    Pix
    -0.06
    POSITIVE LOGITS
    _ra
    0.07
    _monitor
    0.07
     vysvět
    0.07
     Thomas
    0.06
     MODIFY
    0.06
     يح
    0.06
    acional
    0.06
     subsid
    0.06
     органи
    0.06
    Thomas
    0.06
    Act Density 0.002%

    No Known Activations