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

    Neuronpedia

    INDEX
    Explanations

    pose

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    وت
    -0.07
    à
    -0.07
    金融服务
    -0.07
    峪
    -0.06
    ,u
    -0.06
    ileen
    -0.06
    能量
    -0.06
    渺
    -0.06
     Rot
    -0.06
     JT
    -0.06
    POSITIVE LOGITS
     unzip
    0.07
     Caught
    0.07
     feminism
    0.06
     shaking
    0.06
     broadcasts
    0.06
    text
    0.06
     freshmen
    0.06
    (balance
    0.06
    楯
    0.06
     religion
    0.06
    Act Density 0.002%

    No Known Activations