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

    Neuronpedia

    INDEX
    Explanations

    code/internet content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Often
    -0.08
    336
    -0.07
    atri
    -0.07
     OMIT
    -0.07
    olar
    -0.07
     births
    -0.07
     enjoys
    -0.07
    /sm
    -0.07
     Adri
    -0.07
    Staff
    -0.06
    POSITIVE LOGITS
     getUrl
    0.07
    Lesson
    0.06
    toLocale
    0.06
     violated
    0.06
    ์ก
    0.06
    appoint
    0.06
     curly
    0.06
    :SetPoint
    0.06
     =>
    0.06
    될
    0.06
    Act Density 0.065%

    No Known Activations