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

    Neuronpedia

    INDEX
    Explanations

    extracting information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nicely
    -0.09
     סטר
    -0.08
     اسٽ
    -0.08
    forest
    -0.08
    stan
    -0.08
     meadow
    -0.08
     Rd
    -0.08
     מוק
    -0.08
    آ
    -0.07
     lokaci
    -0.07
    POSITIVE LOGITS
     differences
    0.09
     learn
    0.09
    そこ
    0.09
     therein
    0.09
     learning
    0.09
     apprendre
    0.08
     glean
    0.08
     lære
    0.08
     dissect
    0.08
     सीख
    0.08
    Act Density 0.057%

    No Known Activations