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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric probability values (especially floating‐point numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     }:
    -0.07
    (sn
    -0.06
     podnik
    -0.06
    TestCategory
    -0.06
    今
    -0.06
    -offsetof
    -0.06
    ческих
    -0.06
     reactive
    -0.06
    _%
    -0.06
    етич
    -0.06
    POSITIVE LOGITS
     Licht
    0.07
    	point
    0.07
    ]=$
    0.06
     lights
    0.06
     featured
    0.06
    Finite
    0.06
     boom
    0.06
     Lights
    0.06
     운동
    0.06
     "')
    0.06
    Act Density 0.001%

    No Known Activations