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

    Neuronpedia

    INDEX
    Explanations

    static keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     आईं
    0.99
    𝓵
    0.98
    Encycl
    0.98
    மேலும்
    0.97
     त्यामुळे
    0.97
    chloro
    0.96
    𝓷
    0.96
    লিখ
    0.95
    ल
    0.95
     luat
    0.95
    POSITIVE LOGITS
    中
    0.99
     amplitude
    0.99
    ets
    0.94
    การณ์
    0.92
    hape
    0.92
     decrement
    0.91
     Magnitude
    0.89
     sido
    0.89
     Void
    0.88
    कर्ता
    0.87
    Act Density 0.000%

    No Known Activations