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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🎾
    -0.07
    蚴
    -0.07
    علا
    -0.07
    ainer
    -0.07
     voy
    -0.07
    沫
    -0.07
    ağını
    -0.07
     YELLOW
    -0.07
     geniş
    -0.07
    饽
    -0.07
    POSITIVE LOGITS
     burns
    0.07
     authority
    0.07
    _Details
    0.07
    ty
    0.07
    Þ
    0.07
    ferred
    0.07
     association
    0.07
    _err
    0.06
    --;↵↵
    0.06
     thêm
    0.06
    Act Density 0.075%

    No Known Activations