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

    Neuronpedia

    INDEX
    Explanations

    code and variables

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tx
    -0.07
     analyzer
    -0.07
    Analyzer
    -0.07
     legality
    -0.07
    자료
    -0.06
    きた
    -0.06
    _No
    -0.06
     generar
    -0.06
     SHIFT
    -0.06
     succès
    -0.06
    POSITIVE LOGITS
    _states
    0.06
     dost
    0.06
    setDisplay
    0.06
    Κ
    0.06
     (:
    0.06
     Cena
    0.06
     uy
    0.06
    ampoline
    0.06
    eşit
    0.06
    angement
    0.06
    Act Density 0.013%

    No Known Activations