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

    Neuronpedia

    INDEX
    Explanations

    file path components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ت
    1.66
    ש
    1.61
    에
    1.59
    ە
    1.52
    YER
    1.38
    ो
    1.34
    อุ
    1.33
    ariye
    1.32
    اس
    1.31
    ע
    1.30
    POSITIVE LOGITS
    annya
    1.47
    ли
    1.43
    ></
    1.05
    ныя
    1.02
    iendo
    1.01
    >());
    0.98
     perox
    0.96
    вые
    0.96
    !("
    0.96
    ]")
    0.95
    Act Density 0.012%

    No Known Activations