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

    Neuronpedia

    INDEX
    Explanations

    detained

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -mile
    -0.07
    _PLAY
    -0.06
    _minute
    -0.06
     inet
    -0.06
    _sup
    -0.06
     Patio
    -0.06
     taşın
    -0.06
    _BUFF
    -0.06
     ""),
    -0.05
    ONE
    -0.05
    POSITIVE LOGITS
    /fr
    0.07
    grounds
    0.07
     huz
    0.06
     нік
    0.06
     деле
    0.06
    /lib
    0.06
     perf
    0.06
     Milli
    0.06
     documentation
    0.06
     jc
    0.06
    Act Density 0.011%

    No Known Activations