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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Positive
    -0.07
    ippet
    -0.06
     рань
    -0.06
    lendirme
    -0.06
    FAILED
    -0.06
     свое
    -0.06
     practise
    -0.06
     fools
    -0.06
     někdo
    -0.06
    _folders
    -0.06
    POSITIVE LOGITS
    atore
    0.08
     moder
    0.07
    porto
    0.07
    Mex
    0.07
    .help
    0.06
    tr
    0.06
    _TYPE
    0.06
    ーマ
    0.06
     Rath
    0.06
    くらい
    0.06
    Act Density 0.000%

    No Known Activations