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

    Neuronpedia

    INDEX
    Explanations

    code and math formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     있는데
    -0.07
     dei
    -0.07
    𫓹
    -0.07
    指责
    -0.06
    쵸
    -0.06
    ydı
    -0.06
    なくて
    -0.06
     knew
    -0.06
    velt
    -0.06
    ."<
    -0.06
    POSITIVE LOGITS
     stagger
    0.07
    理发
    0.07
    𝐵
    0.07
    نتائ
    0.07
     PLAN
    0.07
    #else
    0.07
     investigate
    0.07
     referral
    0.07
    探究
    0.06
    为一体
    0.06
    Act Density 0.015%

    No Known Activations