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

    Neuronpedia

    INDEX
    Explanations

    podium

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (e
    -0.08
    字符
    -0.07
     If
    -0.07
    吸
    -0.07
    -0.07
     green
    -0.07
    ,m
    -0.07
    enter
    -0.07
    致富
    -0.07
    -width
    -0.07
    POSITIVE LOGITS
     האו
    0.07
     Ông
    0.07
    tığımız
    0.07
    嗪
    0.07
     Rav
    0.06
    olis
    0.06
     Palestin
    0.06
     nhờ
    0.06
    ㎖
    0.06
     lod
    0.06
    Act Density 0.002%

    No Known Activations