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

    Neuronpedia

    INDEX
    Explanations

    True

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     TextArea
    -0.08
    计较
    -0.07
    .zz
    -0.07
    สงบ
    -0.07
    adaş
    -0.07
    (recv
    -0.06
     Qed
    -0.06
    밪
    -0.06
     vase
    -0.06
     boca
    -0.06
    POSITIVE LOGITS
    섬
    0.08
    𝑃
    0.08
    进程中
    0.07
     ----------------
    0.07
     数据
    0.07
     τ
    0.07
     округ
    0.07
     Transform
    0.07
     uncompressed
    0.07
    ingerprint
    0.07
    Act Density 0.001%

    No Known Activations