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

    Neuronpedia

    INDEX
    Explanations

    rare

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eced
    -0.08
    尽头
    -0.08
    sx
    -0.08
     themes
    -0.07
    적
    -0.07
    (inp
    -0.07
    骎
    -0.07
    /temp
    -0.07
    opp
    -0.07
     wb
    -0.07
    POSITIVE LOGITS
     użytkow
    0.07
     didSelectRowAtIndexPath
    0.07
    строен
    0.07
    🍵
    0.07
    רית
    0.07
     rare
    0.07
    悌
    0.06
    0.06
     gri
    0.06
     karde
    0.06
    Act Density 0.009%

    No Known Activations