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

    Neuronpedia

    INDEX
    Explanations

    descriptions of states/events

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens—especially numbers with digits or decimal points.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    throat
    -0.06
    EI
    -0.06
    (Media
    -0.06
    -в
    -0.06
     plus
    -0.06
    nge
    -0.06
     Statue
    -0.06
     slur
    -0.06
     التس
    -0.06
    lope
    -0.06
    POSITIVE LOGITS
     genellikle
    0.07
    <dim
    0.06
    <table
    0.06
    Gtk
    0.06
    perfect
    0.06
    <l
    0.06
     dependent
    0.06
    )arg
    0.06
     '')↵↵
    0.06
     destroying
    0.06
    Act Density 0.123%

    No Known Activations