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

    Neuronpedia

    INDEX
    Explanations

    non-english scripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MediaQuery
    1.44
    dosage
    1.34
     helical
    1.27
     probative
    1.27
    fov
    1.25
    ্স
    1.24
     బ్రిటిషు
    1.23
     niezb
    1.23
     barbell
    1.22
     interpolated
    1.22
    POSITIVE LOGITS
    byshire
    1.04
    らえる
    0.91
    ら
    0.90
    ön
    0.89
    రం
    0.89
    bye
    0.87
    ל
    0.87
    이상
    0.87
    beitung
    0.87
     छ
    0.86
    Act Density 0.000%

    No Known Activations