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

    Neuronpedia

    INDEX
    Explanations

    visual display

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     in
    1.12
    *
    1.00
    lt
    0.98
    larına
    0.90
     painfully
    0.90
    liği
    0.89
    lé
    0.88
    ही
    0.86
    ري
    0.85
    li
    0.85
    POSITIVE LOGITS
    is
    1.41
    ur
    1.21
    不
    1.13
    T
    1.03
    ות
    0.98
    have
    0.96
    <h4>
    0.95
    it
    0.93
    ના
    0.93
    ag
    0.93
    Act Density 0.012%

    No Known Activations