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

    Neuronpedia

    INDEX
    Explanations

    day

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    环境卫生
    -0.07
    amination
    -0.07
     videos
    -0.07
    Photos
    -0.07
    氣
    -0.07
    核算
    -0.07
     Questions
    -0.07
    纷纷表示
    -0.07
     viagra
    -0.06
    دية
    -0.06
    POSITIVE LOGITS
     서울
    0.08
    три
    0.07
     kullanım
    0.07
     {[
    0.07
    天猫
    0.06
    增值
    0.06
    -St
    0.06
    Opening
    0.06
    Θ
    0.06
    往返
    0.06
    Act Density 0.026%

    No Known Activations