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

    Neuronpedia

    INDEX
    Explanations

    information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Paran
    -0.07
    Azure
    -0.07
    odule
    -0.07
    穴
    -0.07
    逃
    -0.07
    Priority
    -0.07
     detention
    -0.06
    evaluate
    -0.06
    dont
    -0.06
     frowned
    -0.06
    POSITIVE LOGITS
    ላ
    0.07
    髎
    0.07
     helpful
    0.07
     GL
    0.07
    首批
    0.06
    $tpl
    0.06
    %/
    0.06
     setResult
    0.06
    =#{
    0.06
    .tables
    0.06
    Act Density 0.803%

    No Known Activations