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

    Neuronpedia

    INDEX
    Explanations

    pertinent

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    壁纸
    -0.08
     sublic
    -0.07
    ⚜
    -0.07
    皇冠
    -0.07
    RY
    -0.07
    聃
    -0.07
    拖延
    -0.07
     whiteColor
    -0.07
     decor
    -0.07
    cwd
    -0.06
    POSITIVE LOGITS
    ERICAN
    0.07
     perpendicular
    0.07
     ATA
    0.07
     yaşayan
    0.06
     Dun
    0.06
    weather
    0.06
    .be
    0.06
     valleys
    0.06
     tantal
    0.06
    נת
    0.06
    Act Density 0.002%

    No Known Activations