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

    Neuronpedia

    INDEX
    Explanations

    explain the meaning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     piccoli
    0.47
     μικ
    0.44
     Auff
    0.44
     kurze
    0.44
    hrt
    0.43
     Vorsch
    0.43
     svojoj
    0.43
    ્સ
    0.43
    sensitivity
    0.42
     Schule
    0.42
    POSITIVE LOGITS
     disqual
    0.45
    ంలో
    0.44
     लेके
    0.44
     pénétr
    0.44
     обязан
    0.44
     yield
    0.42
    تنا
    0.42
    मां
    0.42
    دهای
    0.42
    マー
    0.41
    Act Density 0.000%

    No Known Activations