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

    Neuronpedia

    INDEX
    Explanations

    technical/scientific writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _nav
    -0.07
    lets
    -0.06
     České
    -0.06
    cate
    -0.06
     아주
    -0.06
    _SUITE
    -0.06
    िभ
    -0.06
    輔
    -0.06
    νει
    -0.06
    (reordered
    -0.06
    POSITIVE LOGITS
     experiences
    0.07
    걸
    0.07
     demands
    0.07
    Files
    0.07
     morning
    0.07
     proposal
    0.06
    asm
    0.06
     ".$
    0.06
    Digits
    0.06
     Face
    0.06
    Act Density 0.160%

    No Known Activations