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

    Neuronpedia

    INDEX
    Explanations

    hom

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    嗪
    -0.08
    较多
    -0.07
     Philipp
    -0.07
    .minimum
    -0.07
     soldiers
    -0.07
    綦
    -0.07
     forbid
    -0.07
    苴
    -0.06
     gây
    -0.06
    执勤
    -0.06
    POSITIVE LOGITS
    찯
    0.08
    (label
    0.07
    넗
    0.07
    finish
    0.07
    ⯑
    0.07
    千米
    0.06
    /email
    0.06
     élè
    0.06
     sextreffen
    0.06
    久しぶ
    0.06
    Act Density 0.010%

    No Known Activations