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

    Neuronpedia

    INDEX
    Explanations

    equals sign

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <textarea
    -0.08
    asının
    -0.08
     persuasive
    -0.08
     averaged
    -0.08
    usher
    -0.07
     death
    -0.07
     seductive
    -0.07
    :set
    -0.07
     maturation
    -0.07
     gossip
    -0.07
    POSITIVE LOGITS
     multiples
    0.09
     divisible
    0.08
    iever
    0.08
     وجود
    0.08
     рав
    0.08
     Indicates
    0.08
    整数
    0.08
     autorizado
    0.08
     divisor
    0.07
     Fakt
    0.07
    Act Density 0.034%

    No Known Activations