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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _fk
    -0.07
    阜
    -0.07
    中超
    -0.07
    工艺品
    -0.07
    纺
    -0.06
    Mom
    -0.06
    setMessage
    -0.06
    PTR
    -0.06
    	fp
    -0.06
    腒
    -0.06
    POSITIVE LOGITS
    context
    0.08
    'eau
    0.08
     kay
    0.08
     POSIX
    0.07
     presente
    0.07
    践行
    0.07
     las
    0.07
    (sr
    0.07
    ẳng
    0.07
    -picture
    0.07
    Act Density 0.038%

    No Known Activations