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

    Neuronpedia

    INDEX
    Explanations

    Italian verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     примерно
    0.67
    л
    0.61
     меня
    0.59
     бата
    0.59
    г
    0.59
     ограничен
    0.57
     смесь
    0.57
    ют
    0.55
    лен
    0.55
    Ле
    0.55
    POSITIVE LOGITS
     Italian
    1.04
    イタリア
    1.04
     Italians
    0.99
     italian
    0.96
     partecip
    0.93
     protagonists
    0.92
     peculiarity
    0.91
     Sicilian
    0.84
     Istituto
    0.83
    Italian
    0.82
    Act Density 0.017%

    No Known Activations