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

    Neuronpedia

    INDEX
    Explanations

    star classification

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -root
    -0.07
    归属
    -0.07
    פחד
    -0.07
     challenging
    -0.06
     Infinity
    -0.06
    まだまだ
    -0.06
     exhausted
    -0.06
    UU
    -0.06
     Luckily
    -0.06
    нятие
    -0.06
    POSITIVE LOGITS
    arse
    0.08
    いつも
    0.07
    (arc
    0.07
    .getImage
    0.07
    customize
    0.07
    ULAR
    0.07
     обрат
    0.07
    老公
    0.07
    DSP
    0.07
    %^
    0.06
    Act Density 0.002%

    No Known Activations