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

    Neuronpedia

    INDEX
    Explanations

    T words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ри
    1.08
     kompet
    0.98
    r
    0.97
    ag
    0.95
    ek
    0.91
    hemat
    0.90
    を果た
    0.90
     теа
    0.89
    emat
    0.88
     testigo
    0.88
    POSITIVE LOGITS
     prosecution
    1.01
     Prosecution
    0.94
     Nadu
    0.93
     Titans
    0.92
     mT
    0.90
    itius
    0.90
     মাধ্যমিক
    0.88
     evident
    0.87
     PROM
    0.85
    bcrypt
    0.85
    Act Density 0.278%

    No Known Activations