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

    Neuronpedia

    INDEX
    Explanations

    herits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     astr
    -0.07
    ::
    -0.07
     STOP
    -0.07
     giorni
    -0.07
    .handle
    -0.07
     하면
    -0.06
     anni
    -0.06
    /ajax
    -0.06
    　ヽ
    -0.06
     foll
    -0.06
    POSITIVE LOGITS
    |↵
    0.06
    952
    0.06
    861
    0.06
    AFE
    0.06
    imachinery
    0.06
    ntp
    0.06
    _brand
    0.06
     son
    0.06
     iii
    0.06
    цем
    0.05
    Act Density 0.019%

    No Known Activations