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

    Neuronpedia

    INDEX
    Explanations

    angles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Window
    -0.07
    ▸
    -0.07
    attributes
    -0.07
     Uint
    -0.07
     connexion
    -0.06
    /static
    -0.06
    �
    -0.06
     Watch
    -0.06
     anon
    -0.06
    .hl
    -0.06
    POSITIVE LOGITS
    ığ
    0.07
     السي
    0.06
    auty
    0.06
    的颜色
    0.06
    icy
    0.06
    yps
    0.06
    _prom
    0.06
    ,msg
    0.06
    	Page
    0.06
    实验室
    0.06
    Act Density 0.009%

    No Known Activations