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

    Neuronpedia

    INDEX
    Explanations

    code and math related words and characters, including the word "Date"

    oai_token-act-pair · gemini-2.0-flash

    Date

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Efq
    -0.86
     سكانية
    -0.79
     الرياضيه
    -0.77
     esternos
    -0.67
     Jefus
    -0.67
    ⓧ
    -0.66
    onomía
    -0.66
    <bos>
    -0.66
     Anſ
    -0.65
     урна
    -0.65
    POSITIVE LOGITS
     though
    0.60
    rrggbb
    0.57
    stringify
    0.52
    though
    0.52
    (/\
    0.51
     rad
    0.51
     Though
    0.51
    زا
    0.51
    NOPQRST
    0.50
    ($('#
    0.49
    Act Density 1.754%

    No Known Activations