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

    Neuronpedia

    INDEX
    Explanations

    uniformity and distributions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    S
    0.94
    ne
    0.94
     Been
    0.89
    g
    0.88
     Yorkers
    0.83
     সঠিকভাবে
    0.81
    c
    0.80
    蜢
    0.80
    x
    0.80
    lı
    0.79
    POSITIVE LOGITS
    ло
    0.95
    ции
    0.93
    ння
    0.89
    >
    0.89
    ਰ
    0.84
    ור
    0.82
    ร
    0.82
    د
    0.82
    로
    0.82
    ر
    0.81
    Act Density 0.004%

    No Known Activations