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

    Neuronpedia

    INDEX
    Explanations

    salads and dressings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     implic
    -0.07
     RG
    -0.07
    腋
    -0.06
    ircular
    -0.06
    /org
    -0.06
    URY
    -0.06
     modulo
    -0.06
     SMS
    -0.06
    مج
    -0.06
     Auxiliary
    -0.06
    POSITIVE LOGITS
     Updated
    0.07
     latest
    0.07
    反馈
    0.07
    前に
    0.07
    .Ribbon
    0.07
    晗
    0.06
    brush
    0.06
    秆
    0.06
    latex
    0.06
    critical
    0.06
    Act Density 0.006%

    No Known Activations