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

    Neuronpedia

    INDEX
    Explanations

    mi

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ATT
    -0.07
    -tra
    -0.07
     Тому
    -0.07
    Telefono
    -0.06
     ввод
    -0.06
    _compile
    -0.06
    getVar
    -0.06
     bursting
    -0.06
     rooftop
    -0.06
    oor
    -0.06
    POSITIVE LOGITS
     approximately
    0.07
     prevented
    0.07
    ublisher
    0.06
    pagesize
    0.06
     avant
    0.06
    yclopedia
    0.06
     prevents
    0.06
     bilinen
    0.06
     militias
    0.06
     fills
    0.06
    Act Density 0.003%

    No Known Activations