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

    Neuronpedia

    INDEX
    Explanations

    validation of lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     was
    0.54
     angg
    0.52
    е
    0.51
    }|^
    0.48
     all
    0.48
     direkt
    0.47
     dann
    0.46
     ResponseEntity
    0.44
     köszön
    0.44
     meng
    0.44
    POSITIVE LOGITS
     GUS
    0.43
    infodisc
    0.43
    )>\
    0.43
     индиви
    0.42
    条例
    0.42
    oyloxy
    0.42
     समझा
    0.41
    comstock
    0.41
    ಕ್ಕಿಂತ
    0.41
    saraba
    0.41
    Act Density 0.003%

    No Known Activations