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

    Neuronpedia

    INDEX
    Explanations

    Quantifiers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     menacing
    -0.08
    .account
    -0.07
    ul
    -0.07
     bicycle
    -0.06
    कन
    -0.06
    abies
    -0.06
     demonstrates
    -0.06
     ls
    -0.06
    _trait
    -0.06
     interval
    -0.06
    POSITIVE LOGITS
    .setBorder
    0.06
     документа
    0.06
    网址
    0.06
    entine
    0.06
    .SpringBootApplication
    0.06
     snork
    0.06
    СР
    0.06
     kırmızı
    0.06
    jím
    0.06
     ㅇㅇ
    0.06
    Act Density 0.118%

    No Known Activations