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

    Neuronpedia

    INDEX
    Explanations

    words indicating recent time

    oai_token-act-pair · gemini-2.0-flash

    references to time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CloseOperation
    -0.68
    aarrggbb
    -0.65
    EndInit
    -0.59
     Footh
    -0.56
    jooq
    -0.56
    setViewportView
    -0.56
    tzmann
    -0.55
     equidist
    -0.54
    lético
    -0.52
     Brahmin
    -0.51
    POSITIVE LOGITS
     ago
    0.95
     yesterday
    0.84
    Yesterday
    0.84
    <bos>
    0.81
     fjor
    0.79
     recent
    0.78
     scorso
    0.77
     previous
    0.75
     Yesterday
    0.75
    yesterday
    0.74
    Act Density 0.742%

    No Known Activations