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

    Neuronpedia

    INDEX
    Explanations

    structured comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     сх
    0.41
    淉
    0.40
    px
    0.36
    iciary
    0.36
     दस्ते
    0.36
     pectin
    0.35
    brains
    0.34
    arns
    0.33
    rophot
    0.33
    dtypes
    0.33
    POSITIVE LOGITS
     KIR
    0.42
    }^{-
    0.39
     officer
    0.38
     ^{-
    0.38
     สำ
    0.38
    ಂತ್ರ
    0.38
     participé
    0.38
    Albums
    0.37
    નિક
    0.37
    трима
    0.37
    Act Density 0.003%

    No Known Activations