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

    Neuronpedia

    INDEX
    Explanations

    citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    ．
    -0.07
     bowel
    -0.07
    .multi
    -0.06
    电子
    -0.06
     näch
    -0.06
    _db
    -0.06
     아주
    -0.06
    .daily
    -0.06
    (State
    -0.06
    POSITIVE LOGITS
    hled
    0.07
     Elliot
    0.07
     Developing
    0.07
    Sometimes
    0.07
     Quad
    0.06
    .website
    0.06
    bě
    0.06
    itionally
    0.06
    _COMPAT
    0.06
     Town
    0.06
    Act Density 0.012%

    No Known Activations