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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash

    The neuron fires on the standard “This file is part of …” license‐header line at the top of source files.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    aurants
    -0.07
     gig
    -0.07
    _scheme
    -0.06
    .module
    -0.06
     playwright
    -0.06
    kání
    -0.06
    airro
    -0.06
     Wig
    -0.06
     Participant
    -0.06
    Carousel
    -0.06
    POSITIVE LOGITS
     prav
    0.06
     BufferedWriter
    0.06
    refs
    0.06
     Today
    0.06
    حم
    0.06
     elasticity
    0.06
     Url
    0.06
     actu
    0.06
    eor
    0.05
    /not
    0.05
    Act Density 0.005%

    No Known Activations