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

    Neuronpedia

    INDEX
    Explanations

    mentions of counting, codes, or quantities, sometimes in combination with "up".

    oai_token-act-pair · gemini-2.0-flash

    count

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     صوتيه
    -1.02
     esternos
    -0.99
    PreferredItem
    -0.96
    -0.95
    MENAFN
    -0.95
    makeText
    -0.93
     &___
    -0.91
     كومونز
    -0.88
    IsContent
    -0.88
     <>",
    -0.88
    POSITIVE LOGITS
    share
    0.40
     share
    0.38
    g
    0.36
     present
    0.35
    Share
    0.35
    b
    0.34
    Do
    0.34
     par
    0.34
    offre
    0.34
     baik
    0.34
    Act Density 8.354%

    No Known Activations