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

    Neuronpedia

    INDEX
    Explanations

    Islamic veils

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     citas
    -0.07
    (Runtime
    -0.07
    ฉบ
    -0.07
    纻
    -0.07
    iddled
    -0.06
    olut
    -0.06
    ,cljs
    -0.06
     נית
    -0.06
     wides
    -0.06
     seznam
    -0.06
    POSITIVE LOGITS
     sphere
    0.07
    썹
    0.07
    (resultado
    0.07
    ">--}}↵
    0.07
    ':↵↵
    0.07
    ())↵
    0.07
    white
    0.07
     soma
    0.07
    _Click
    0.07
    ')}}">↵
    0.06
    Act Density 0.011%

    No Known Activations