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

    Neuronpedia

    INDEX
    Explanations

    helpline contact information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Starring
    0.62
    нето
    0.57
    सायनिक
    0.57
     क्रिया
    0.56
     spree
    0.56
    áš
    0.56
     моз
    0.56
    ⬝
    0.55
     Поскольку
    0.55
     democratization
    0.55
    POSITIVE LOGITS
    lant
    0.58
    larına
    0.57
    te
    0.52
    u
    0.48
    tarif
    0.48
    treated
    0.47
    formatter
    0.47
    li
    0.47
    #$%
    0.46
     mie
    0.46
    Act Density 0.443%

    No Known Activations