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

    Neuronpedia

    INDEX
    Explanations

    ranking and reasons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     on
    0.48
    בק
    0.46
    ifferentiate
    0.46
    ])),
    0.45
     rational
    0.44
     Recognizing
    0.43
     স
    0.41
     کرمان
    0.41
     Solubility
    0.40
    呉
    0.40
    POSITIVE LOGITS
     paio
    0.61
    ático
    0.54
     contas
    0.53
     việc
    0.52
    u
    0.50
     montaña
    0.49
     phụ
    0.49
    ım
    0.49
    órico
    0.48
    IdleSync
    0.47
    Act Density 0.010%

    No Known Activations