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

    Neuronpedia

    INDEX
    Explanations

    algorithm, arithmetic, atmospheric

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    كان
    0.86
    د
    0.86
    д
    0.79
    ১
    0.69
    ل
    0.67
    த
    0.66
    و
    0.66
    بر
    0.65
    其他
    0.64
     canciones
    0.63
    POSITIVE LOGITS
    2
    1.13
    0
    0.96
    8
    0.85
    ric
    0.82
    ну
    0.82
    ę
    0.78
    :
    0.75
    ן
    0.75
    ્ય
    0.73
    7
    0.73
    Act Density 0.353%

    No Known Activations