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

    Neuronpedia

    INDEX
    Explanations

    non-English words or phrases

    oai_token-act-pair · gemini-2.0-flash

    Greetings and Swedish language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -1.95
     the
    -0.73
    ↵↵
    -0.65
    '
    -0.60
    ’
    -0.56
     The
    -0.54
    ↵
    -0.54
     a
    -0.48
     der
    -0.47
    /*
    -0.46
    POSITIVE LOGITS
     quæ
    0.78
     Banker
    0.75
    BeginInit
    0.73
     swimmer
    0.73
     Mongols
    0.73
    SuccessListener
    0.71
     Engra
    0.71
     urethra
    0.71
     AssemblyCulture
    0.70
     humaine
    0.70
    Act Density 0.288%

    No Known Activations