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

    Neuronpedia

    INDEX
    Explanations

    camera aperture

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fulfillment
    -0.07
    uvial
    -0.07
    Markdown
    -0.07
     embed
    -0.07
     edema
    -0.07
     embrace
    -0.07
     Markdown
    -0.07
     goodbye
    -0.07
    /manual
    -0.07
     interview
    -0.07
    POSITIVE LOGITS
    是多少
    0.09
     chemin
    0.08
     ontstaan
    0.08
     Faktor
    0.08
    等级
    0.08
     imponer
    0.08
    entrale
    0.07
     dhu
    0.07
    .Fast
    0.07
    ength
    0.07
    Act Density 0.002%

    No Known Activations