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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Swedish
    -0.07
     prat
    -0.07
     foyer
    -0.07
     मश
    -0.06
    _adv
    -0.06
     distraction
    -0.06
     LJ
    -0.06
    yla
    -0.06
    游戏
    -0.06
    ｯ
    -0.06
    POSITIVE LOGITS
     상
    0.07
    ــــ
    0.06
    _DIALOG
    0.06
    .createSequentialGroup
    0.06
    *))
    0.06
    )[
    0.06
    putc
    0.06
     signature
    0.06
     عبار
    0.06
    inars
    0.06
    Act Density 0.028%

    No Known Activations