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

    Neuronpedia

    INDEX
    Explanations

    his

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _slider
    -0.07
    092
    -0.07
    iclass
    -0.06
     Interstate
    -0.06
    _SI
    -0.06
    Bộ
    -0.06
    前に
    -0.06
     ___
    -0.06
    영
    -0.06
    cascade
    -0.06
    POSITIVE LOGITS
     perpetrator
    0.07
    dio
    0.07
     Harmon
    0.06
     اختل
    0.06
     vyj
    0.06
     применя
    0.06
    _progress
    0.06
    apos
    0.06
     boils
    0.06
    -shift
    0.06
    Act Density 0.012%

    No Known Activations