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

    Neuronpedia

    INDEX
    Explanations

    fresh perspective, review

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     المعروف
    -0.08
     prior
    -0.08
    preced
    -0.08
     suppos
    -0.08
    usión
    -0.08
     محفوظ
    -0.08
     priorité
    -0.07
    яз
    -0.07
    Prior
    -0.07
     contingency
    -0.07
    POSITIVE LOGITS
     Bewertung
    0.08
     imagined
    0.08
    iffs
    0.08
    .maps
    0.08
    看看
    0.08
     Deletes
    0.07
     Comparing
    0.07
     nähdä
    0.07
     Checks
    0.07
    仔
    0.07
    Act Density 0.011%

    No Known Activations