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

    Neuronpedia

    INDEX
    Explanations

    Scientific descriptions

    np_max-act · gemini-2.0-flash

    The neuron selectively fires on numeric measurement tokens—decimal numbers, percentages, and other measurement values in the strain descriptions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     フ
    -0.07
     Coat
    -0.07
    aller
    -0.06
     Wall
    -0.06
     inté
    -0.06
     dB
    -0.06
     Coff
    -0.06
    无法
    -0.06
    _PLAYER
    -0.06
     imz
    -0.06
    POSITIVE LOGITS
     juven
    0.07
     imply
    0.06
    ♪
    0.06
     swim
    0.06
     sincerely
    0.06
    (cart
    0.06
    _dw
    0.06
    (rot
    0.06
    lijke
    0.06
     sy
    0.06
    Act Density 0.010%

    No Known Activations