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

    Neuronpedia

    INDEX
    Explanations

    words in multiple languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )。
    0.84
    )'
    0.83
    ↵↵
    0.82
    de
    0.79
    ective
    0.78
    lhe
    0.77
    d
    0.77
    ॠ
    0.77
    féle
    0.75
    。"
    0.75
    POSITIVE LOGITS
     cinco
    1.07
     quatro
    1.03
     wielu
    1.02
     muchos
    0.98
     कई
    0.96
     muitas
    0.95
     всех
    0.95
     quatre
    0.94
     многие
    0.93
     многих
    0.91
    Act Density 0.096%

    No Known Activations