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

    Neuronpedia

    INDEX
    Explanations

    signed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     equivalence
    -0.07
     اختیار
    -0.07
    Attack
    -0.07
    mob
    -0.07
    Creature
    -0.06
    ‌ی
    -0.06
     fractures
    -0.06
    REMOVE
    -0.06
     мину
    -0.06
    imizin
    -0.06
    POSITIVE LOGITS
    -signed
    0.07
    �
    0.06
     Signed
    0.06
    گان
    0.06
     Napoli
    0.06
    	Assert
    0.06
     signed
    0.06
     UNSIGNED
    0.06
    	g
    0.06
    _UNSIGNED
    0.06
    Act Density 0.002%

    No Known Activations