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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric literal tokens (especially floating-point numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ImageButton
    -0.07
    >>();↵↵
    -0.06
    &,
    -0.06
    _mp
    -0.06
    .notifyDataSetChanged
    -0.06
    ,
↵
    -0.06
    disp
    -0.06
    лим
    -0.06
    λλά
    -0.06
    Comments
    -0.06
    POSITIVE LOGITS
    	height
    0.07
     sırada
    0.07
    vents
    0.06
     Modeling
    0.06
    (Duration
    0.06
     Session
    0.06
    ellers
    0.06
     줄
    0.06
    iculos
    0.06
    spread
    0.06
    Act Density 0.202%

    No Known Activations