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

    Neuronpedia

    INDEX
    Explanations

    Gateway, default

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	utils
    -0.08
    (cancel
    -0.07
     Wisdom
    -0.07
     terrace
    -0.07
    最主要
    -0.07
     vacuum
    -0.07
    .doc
    -0.07
     Cheap
    -0.07
     indications
    -0.07
    adget
    -0.07
    POSITIVE LOGITS
    ()↵↵
    0.07
    ’t
    0.07
    kaar
    0.07
     gathered
    0.07
    >");↵
    0.07
    ሽ
    0.07
    Remember
    0.06
    iking
    0.06
     nginx
    0.06
    进出
    0.06
    Act Density 0.006%

    No Known Activations