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

    Neuronpedia

    INDEX
    Explanations

    tokenization and tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Viola
    1.08
     Assuming
    1.06
     таки
    1.06
    док
    1.05
    ded
    1.03
     потреби
    1.03
    raphe
    1.03
    dna
    1.02
    led
    1.01
     acost
    1.00
    POSITIVE LOGITS
    ꒷
    1.27
     pona
    1.17
    पर्यंत
    1.08
    鹸
    1.05
     getToken
    1.04
    न्ही
    1.04
    ized
    1.03
     Abgerufen
    1.02
    $("#
    1.01
     backsplash
    1.00
    Act Density 0.078%

    No Known Activations