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

    Neuronpedia

    INDEX
    Explanations

    were

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     crappy
    -0.06
    quiz
    -0.06
    ClassName
    -0.06
     lz
    -0.06
    미
    -0.06
    kas
    -0.06
    otechnology
    -0.06
    ylinder
    -0.05
     HBO
    -0.05
     Av
    -0.05
    POSITIVE LOGITS
     applicationWill
    0.07
    -billion
    0.07
    ainting
    0.07
     erotic
    0.07
    RenderingContext
    0.07
    rang
    0.07
     東京
    0.07
     casual
    0.07
    型
    0.06
    lea
    0.06
    Act Density 0.017%

    No Known Activations