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

    Neuronpedia

    INDEX
    Explanations

    I don

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     недоста
    0.47
     lacking
    0.44
     lack
    0.43
     nedost
    0.43
     initially
    0.40
    &
    0.40
     missing
    0.39
     отсутствие
    0.38
    Missing
    0.38
    iliter
    0.38
    POSITIVE LOGITS
     ambivalent
    0.42
     privilegi
    0.38
     స్థ
    0.37
    蝣
    0.37
     oscillator
    0.37
     chanc
    0.37
     ยาว
    0.36
    phosph
    0.34
     senjata
    0.34
    ंठ
    0.34
    Act Density 0.003%

    No Known Activations