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

    Neuronpedia

    INDEX
    Explanations

    distribution

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reput
    -0.07
    _cmp
    -0.07
    𐍃
    -0.07
     컴퓨
    -0.07
     neigh
    -0.07
    не
    -0.07
    男神
    -0.07
     gymn
    -0.06
     logistical
    -0.06
     setBackgroundImage
    -0.06
    POSITIVE LOGITS
     efect
    0.07
    使用寿命
    0.07
    *b
    0.07
    屉
    0.07
     options
    0.07
    흩
    0.07
    _caption
    0.07
    ________
    0.06
    ㎟
    0.06
    BB
    0.06
    Act Density 0.001%

    No Known Activations