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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    أ
    -0.07
    	task
    -0.07
     fie
    -0.07
     ×
    -0.06
    остью
    -0.06
     тради
    -0.06
     Prize
    -0.06
    枪
    -0.06
     neredeyse
    -0.06
     Wy
    -0.06
    POSITIVE LOGITS
     EZ
    0.06
     atoi
    0.06
    815
    0.06
    	ID
    0.06
     setEmail
    0.06
    クロ
    0.06
     can
    0.06
     explain
    0.06
    'A
    0.06
     getAll
    0.06
    Act Density 0.006%

    No Known Activations