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

    Neuronpedia

    INDEX
    Explanations

    unpublished

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ưỡng
    -0.07
    Signature
    -0.07
    panic
    -0.07
    ¡
    -0.07
    臀
    -0.06
    拍照
    -0.06
    anh
    -0.06
    egal
    -0.06
    _util
    -0.06
    raud
    -0.06
    POSITIVE LOGITS
     fácil
    0.07
    副校长
    0.07
     público
    0.07
     hbox
    0.07
     условия
    0.06
     boys
    0.06
     unthinkable
    0.06
     opened
    0.06
     movable
    0.06
     speakers
    0.06
    Act Density 0.000%

    No Known Activations