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

    Neuronpedia

    INDEX
    Explanations

    geometry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     imposed
    -0.08
     바랍니다
    -0.08
     unlimited
    -0.08
    fait
    -0.08
     añade
    -0.08
     hos
    -0.08
     단계
    -0.08
     accepted
    -0.08
     دی
    -0.07
     받고
    -0.07
    POSITIVE LOGITS
     originally
    0.09
    δας
    0.09
    _original
    0.09
    ώνα
    0.09
    位置
    0.08
    .rotate
    0.08
    的位置
    0.08
    (original
    0.08
    Originally
    0.08
     Originally
    0.08
    Act Density 0.017%

    No Known Activations