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

    Neuronpedia

    INDEX
    Explanations

    head coverings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ames
    -0.08
    面条
    -0.07
    	trace
    -0.07
    地道
    -0.07
    lay
    -0.07
    -rays
    -0.07
    looking
    -0.07
    path
    -0.07
    seys
    -0.07
    探し
    -0.07
    POSITIVE LOGITS
    angible
    0.07
     "\",
    0.07
    \":{\"
    0.07
     */}↵
    0.07
     unanswered
    0.06
     renewable
    0.06
    ";
↵
    0.06
     مختلفة
    0.06
    **
↵
    0.06
     Anita
    0.06
    Act Density 0.009%

    No Known Activations