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

    Neuronpedia

    INDEX
    Explanations

    Local family experiences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    סטר
    -0.07
     الرو
    -0.07
     Mao
    -0.07
    ינ
    -0.07
     ancora
    -0.07
     employers
    -0.07
     su
    -0.06
    ische
    -0.06
    𝕝
    -0.06
    立ち
    -0.06
    POSITIVE LOGITS
    /themes
    0.09
     contag
    0.07
    .Rad
    0.07
    คม
    0.07
    盼
    0.07
     petals
    0.06
     '.',
    0.06
    Damn
    0.06
     "":↵
    0.06
     -(
    0.06
    Act Density 0.047%

    No Known Activations