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

    Neuronpedia

    INDEX
    Explanations

    text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	required
    -0.07
     droits
    -0.06
    _PRIMARY
    -0.06
    .sz
    -0.06
     subdued
    -0.06
     Humanities
    -0.06
    -language
    -0.06
    .Repository
    -0.06
    (position
    -0.06
     바라
    -0.06
    POSITIVE LOGITS
    篇
    0.08
     tyr
    0.07
     Tyr
    0.07
     TOUCH
    0.07
    -too
    0.07
     体
    0.07
     pam
    0.06
    ск
    0.06
    ший
    0.06
     flux
    0.06
    Act Density 0.021%

    No Known Activations