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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    colors
    -0.07
    -help
    -0.06
    197
    -0.06
    рана
    -0.06
     diarr
    -0.06
    Va
    -0.06
    .help
    -0.06
    ्रव
    -0.06
    Certain
    -0.06
     rav
    -0.06
    POSITIVE LOGITS
    _process
    0.07
    <lemma
    0.07
    ,date
    0.07
    .ColumnName
    0.06
     увид
    0.06
    �
    0.06
    ual
    0.06
     Ú
    0.06
     �
    0.06
     gather
    0.06
    Act Density 0.001%

    No Known Activations