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

    Neuronpedia

    INDEX
    Explanations

    minor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -q
    -0.07
    svm
    -0.07
    (cos
    -0.07
    	boost
    -0.07
    	synchronized
    -0.06
     resonate
    -0.06
     ee
    -0.06
    恸
    -0.06
     cleansing
    -0.06
    Exclude
    -0.06
    POSITIVE LOGITS
     Körper
    0.08
    ใส
    0.07
    Ἥ
    0.07
    מספר
    0.07
     Marilyn
    0.07
     habitats
    0.07
    .[
    0.07
    ()[
    0.06
     FORM
    0.06
    .rule
    0.06
    Act Density 0.004%

    No Known Activations