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

    Neuronpedia

    INDEX
    Explanations

    lists with bullet points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bank
    0.48
     ಸ್ಪ
    0.47
     села
    0.45
     Attractive
    0.44
    urant
    0.42
     Quar
    0.41
    town
    0.41
     Pending
    0.41
     Districts
    0.41
     ξ
    0.41
    POSITIVE LOGITS
    しなければ
    0.48
    ترى
    0.48
     kaldığımız
    0.46
     superstitious
    0.45
    ビー
    0.44
    EMBER
    0.43
    schaft
    0.42
    那么
    0.41
     carcin
    0.41
    挪
    0.40
    Act Density 0.001%

    No Known Activations