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

    Neuronpedia

    INDEX
    Explanations

    programming questions/answers

    np_max-act · gemini-2.0-flash

    The neuron responds to numeric tokens, particularly floating-point numbers (decimal values).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     wordt
    -0.07
     frames
    -0.06
     kill
    -0.06
     conveyor
    -0.06
    craft
    -0.06
     seen
    -0.06
     Đông
    -0.06
     feed
    -0.06
    	object
    -0.06
     frequ
    -0.06
    POSITIVE LOGITS
     <$>
    0.07
    ประสบ
    0.07
    _LEG
    0.06
     disadv
    0.06
     FOREIGN
    0.06
     benim
    0.06
    Apollo
    0.06
     _|
    0.06
    .primary
    0.06
    جميع
    0.06
    Act Density 0.042%

    No Known Activations