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

    Neuronpedia

    INDEX
    Explanations

    technology standards

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     filed
    -0.07
     Facility
    -0.07
     misogyn
    -0.07
    ότε
    -0.06
     finalists
    -0.06
    								
↵
    -0.06
     nhất
    -0.06
    .keys
    -0.06
    ління
    -0.06
    mět
    -0.06
    POSITIVE LOGITS
    .CODE
    0.07
     chai
    0.07
     voucher
    0.06
    개발
    0.06
    .toFixed
    0.06
     Respir
    0.06
    cmp
    0.06
     ROC
    0.06
    eight
    0.06
    信息
    0.06
    Act Density 0.046%

    No Known Activations