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

    Neuronpedia

    INDEX
    Explanations

    serial

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    documento
    -0.07
     доп
    -0.07
    　ﾉ
    -0.07
    .nan
    -0.06
    озна
    -0.06
     щодо
    -0.06
    층
    -0.06
     phosph
    -0.06
     зем
    -0.06
    -Agent
    -0.06
    POSITIVE LOGITS
    discard
    0.07
    igr
    0.06
    ig
    0.06
    lar
    0.06
     �
    0.06
    ี.
    0.06
     dedication
    0.06
     peril
    0.06
     wounded
    0.06
     serial
    0.06
    Act Density 0.007%

    No Known Activations