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

    Neuronpedia

    INDEX
    Explanations

    LaTeX

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    认为
    -0.07
     dağı
    -0.06
     Lang
    -0.06
     нич
    -0.06
    (jsonObject
    -0.06
    位於
    -0.06
     gle
    -0.06
    .*;
↵
    -0.06
     independ
    -0.06
    되었습니다
    -0.06
    POSITIVE LOGITS
    .getDay
    0.07
    شة
    0.07
    ferences
    0.07
    ISHED
    0.07
    rego
    0.07
    HomeAs
    0.06
     segue
    0.06
    avings
    0.06
     Floor
    0.06
    chos
    0.06
    Act Density 0.003%

    No Known Activations