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

    Neuronpedia

    INDEX
    Explanations

    short, common words and prepositions

    oai_token-act-pair · gemini-2.0-flash

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.76
     ostavi
    -0.73
    Билгалдахарш
    -0.70
     تانيه
    -0.69
     <<<<<<<<<<<<<<
    -0.68
    didSet
    -0.65
     kasarigan
    -0.62
     häm
    -0.62
    intios
    -0.61
    colgroup
    -0.61
    POSITIVE LOGITS
     active
    0.48
     aids
    0.42
     available
    0.40
    znam
    0.40
    Referanser
    0.40
    bory
    0.40
    weich
    0.40
    enegro
    0.39
    бенок
    0.39
     Cor
    0.38
    Act Density 4.136%

    No Known Activations