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

    Neuronpedia

    INDEX
    Explanations

    has

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    「そう
    -0.07
    Το
    -0.07
     decir
    -0.06
    كييف
    -0.06
    NFL
    -0.06
    UFFIX
    -0.06
    Im
    -0.06
     thế
    -0.06
    ์และ
    -0.06
     شاهد
    -0.06
    POSITIVE LOGITS
    _mE
    0.08
    증금
    0.07
     přih
    0.06
    venida
    0.06
    -income
    0.06
    _cores
    0.06
     represents
    0.06
    .fml
    0.06
    .codes
    0.06
     Interr
    0.06
    Act Density 0.004%

    No Known Activations