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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Counter
    -0.07
    enties
    -0.07
     cautious
    -0.07
    夏季
    -0.07
    inc
    -0.06
     McCoy
    -0.06
     getPrice
    -0.06
    icionar
    -0.06
    pector
    -0.06
    抗生素
    -0.06
    POSITIVE LOGITS
    _absolute
    0.08
    됄
    0.06
    皆
    0.06
    〵
    0.06
    _elems
    0.06
     marvelous
    0.06
    _domain
    0.06
     عبد
    0.06
    &type
    0.06
     superclass
    0.06
    Act Density 0.019%

    No Known Activations