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

    Neuronpedia

    INDEX
    Explanations

    scientific citations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    valuation
    -0.09
    (TypeError
    -0.08
    Singapore
    -0.07
    さらに
    -0.07
    在未来
    -0.07
    出示
    -0.07
     LICENSE
    -0.07
    ước
    -0.07
    forms
    -0.07
    lernen
    -0.07
    POSITIVE LOGITS
    דיר
    0.07
     acct
    0.07
     BAR
    0.06
     pkt
    0.06
    pton
    0.06
     Suit
    0.06
     pundits
    0.06
     pard
    0.06
     [],
↵
    0.06
     Asi
    0.06
    Act Density 0.002%

    No Known Activations