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

    Neuronpedia

    INDEX
    Explanations

    words and phrases relating to statistical accounting

    oai_token-act-pair · gemini-2.0-flash

    account

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gynhyrchwyd
    -1.06
     فريبيس
    -1.02
     Efq
    -0.98
     Monfieur
    -0.94
     themſelves
    -0.93
     ―――――
    -0.90
     Theſe
    -0.90
     myſelf
    -0.85
     itſelf
    -0.83
     GoogleFonts
    -0.83
    POSITIVE LOGITS
     
    0.63
     half
    0.50
    by
    0.47
     :
    0.46
    half
    0.45
    <eos>
    0.45
    .
    0.44
    :
    0.42
    ’
    0.41
     $
    0.41
    Act Density 2.596%

    No Known Activations