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

    Neuronpedia

    INDEX
    Explanations

    lists and breakdowns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ২০১৬
    0.46
     WALTER
    0.46
     रूई
    0.43
     eBooks
    0.43
     Cellular
    0.43
     Shirts
    0.43
     StringIO
    0.43
     Pounds
    0.43
    मित्व
    0.42
     တော့
    0.41
    POSITIVE LOGITS
    ous
    0.45
    tten
    0.44
     debout
    0.42
    ús
    0.42
     रोपवे
    0.42
    JK
    0.41
    ungk
    0.41
    sts
    0.41
    ૈ
    0.41
    АР
    0.40
    Act Density 0.010%

    No Known Activations