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

    Neuronpedia

    INDEX
    Explanations

    natural to feel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⃣
    0.90
    它
    0.86
    ️⃣
    0.83
    માં
    0.80
    พื้นที่
    0.79
    אר
    0.76
    ține
    0.76
    Bits
    0.75
    aisu
    0.74
    ículos
    0.73
    POSITIVE LOGITS
    e
    0.83
    क
    0.76
    o
    0.75
    k
    0.71
     T
    0.69
     S
    0.68
     знамена
    0.68
    re
    0.68
    V
    0.68
     gevallen
    0.67
    Act Density 0.046%

    No Known Activations