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

    Neuronpedia

    INDEX
    Explanations

    Hor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     banquet
    -0.07
    (Class
    -0.06
    (Size
    -0.06
    เฉล
    -0.06
    (add
    -0.06
    研
    -0.06
    _distribution
    -0.06
    (['/
    -0.06
     quilt
    -0.06
    .frequency
    -0.06
    POSITIVE LOGITS
     Hor
    0.38
    Hor
    0.27
     hor
    0.17
     HOR
    0.16
    hor
    0.14
     Horizon
    0.10
    _hor
    0.10
     hors
    0.09
     horror
    0.09
    _HOR
    0.08
    Act Density 0.010%

    No Known Activations