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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     superv
    -0.08
    Fran
    -0.07
    .watch
    -0.06
    .ch
    -0.06
     Bern
    -0.06
     halten
    -0.06
     Abu
    -0.06
     نامه
    -0.06
     eleven
    -0.06
    以来
    -0.06
    POSITIVE LOGITS
    iconductor
    0.07
    [data
    0.06
     důležité
    0.06
     hangi
    0.06
    ٍ
    0.06
    ůležit
    0.06
     αστ
    0.06
    entario
    0.06
    rowData
    0.06
    qed
    0.06
    Act Density 0.008%

    No Known Activations