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

    Neuronpedia

    INDEX
    Explanations

    JSON configuration and commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ו
    1.18
    iin
    1.14
    ی
    1.12
    each
    1.09
    יות
    1.04
    een
    1.00
    ił
    1.00
    es
    0.99
    י
    0.98
    ipped
    0.97
    POSITIVE LOGITS
    शील
    0.92
     afterDir
    0.91
     [],
    0.91
     $|\
    0.90
    ını
    0.88
    ")),
    0.88
    ാൻ
    0.87
    वहीं
    0.85
    moja
    0.84
     CURLOPT
    0.83
    Act Density 0.001%

    No Known Activations