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

    Neuronpedia

    INDEX
    Explanations

    type of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ന്‍
    1.05
     nichts
    1.05
     ī
    1.03
     Dés
    1.03
     dé
    0.97
    ayn
    0.96
    abilidad
    0.95
    ൯
    0.95
    就连
    0.94
    स्थ
    0.93
    POSITIVE LOGITS
     kelamin
    1.28
    ান্তরে
    1.22
    SACTION
    1.12
     hình
    1.06
     tetrachloride
    1.04
    hình
    1.03
    ique
    1.02
    ினான்
    1.00
     господар
    0.98
    IQUE
    0.97
    Act Density 0.426%

    No Known Activations