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

    Neuronpedia

    INDEX
    Explanations

    Start of document/section

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =val
    -0.07
    应当
    -0.07
    _round
    -0.06
    jump
    -0.06
    pressions
    -0.06
    Priority
    -0.06
    スト
    -0.06
    ورن
    -0.06
     plague
    -0.06
     گروه
    -0.06
    POSITIVE LOGITS
     Substance
    0.07
    ​
    0.06
     Approximately
    0.06
     />\
    0.06
    Emergency
    0.06
     strategist
    0.06
    dc
    0.06
     toys
    0.06
     covert
    0.06
     bakery
    0.06
    Act Density 0.002%

    No Known Activations