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

    Neuronpedia

    INDEX
    Explanations

    players

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ula
    -0.07
    (Card
    -0.07
    ULA
    -0.07
     formulas
    -0.07
    ————————————————
    -0.06
    眼睛
    -0.06
     K
    -0.06
     hoax
    -0.06
     endowed
    -0.06
     continued
    -0.06
    POSITIVE LOGITS
     Initializes
    0.06
     /*!<
    0.06
    ISO
    0.06
     lil
    0.06
    判
    0.06
    qt
    0.06
     swept
    0.06
     Nä
    0.06
    	tag
    0.06
     gaz
    0.06
    Act Density 0.010%

    No Known Activations