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

    Neuronpedia

    INDEX
    Explanations

    locking/unlocking code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Заг
    -0.07
    aty
    -0.06
     특별
    -0.06
    homme
    -0.06
     дії
    -0.05
     Mitar
    -0.05
     herself
    -0.05
     الخام
    -0.05
    rous
    -0.05
     vysoké
    -0.05
    POSITIVE LOGITS
     flattering
    0.07
     Front
    0.07
    .bootstrapcdn
    0.07
     jerk
    0.07
     instantiate
    0.07
     offseason
    0.07
     Operational
    0.06
    .Sm
    0.06
     trilogy
    0.06
     |↵↵
    0.06
    Act Density 0.012%

    No Known Activations