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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pills
    -0.07
     располаг
    -0.07
     anniversary
    -0.07
    Anyway
    -0.07
    lardı
    -0.07
    idade
    -0.07
    lıkları
    -0.07
     injection
    -0.06
     еди
    -0.06
     وفي
    -0.06
    POSITIVE LOGITS
    _uc
    0.06
    idges
    0.06
    '#
    0.06
     Rutgers
    0.06
    ghost
    0.06
     centro
    0.06
    ILLE
    0.06
    -powered
    0.06
     Cameron
    0.06
    _ber
    0.05
    Act Density 0.006%

    No Known Activations