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

    Neuronpedia

    INDEX
    Explanations

    code file paths and module names

    oai_token-act-pair · gemini-2.0-flash

    /

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -1.33
     The
    -0.52
     her
    -0.51
     he
    -0.50
     the
    -0.49
     his
    -0.47
    The
    -0.46
     
    -0.46
     الاطلاع
    -0.45
    -
    -0.44
    POSITIVE LOGITS
    Архівовано
    0.71
     Unde
    0.69
     versace
    0.69
     LNB
    0.68
     Riverdale
    0.67
    πως
    0.66
    товано
    0.66
     convertView
    0.66
     Geologist
    0.64
    IndentedString
    0.64
    Act Density 2.149%

    No Known Activations