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

    Neuronpedia

    INDEX
    Explanations

    special characters

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    igold
    0.64
    anto
    0.62
     ($
    0.61
     Kind
    0.56
    antation
    0.56
    Kind
    0.55
    cept
    0.55
    Clone
    0.54
    inya
    0.54
     (+)
    0.54
    POSITIVE LOGITS
     ém
    0.56
    ாக
    0.54
    UEST
    0.54
     보다
    0.53
     역할을
    0.52
     Augen
    0.50
    لہ
    0.47
    সল
    0.47
     INTERNAL
    0.47
     տ
    0.47
    Act Density 0.003%

    No Known Activations