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

    Neuronpedia

    INDEX
    Explanations

    science papers

    np_max-act · gemini-2.0-flash

    The neuron fires on specialized scientific acronyms, model names, and proper‐noun labels (e.g. “FR I,” “BL Lac,” “SED,” etc.) in astrophysics texts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     NAND
    -0.07
    Shift
    -0.06
     intervals
    -0.06
    Vis
    -0.06
     catastrophic
    -0.06
    /tos
    -0.06
     Nacht
    -0.06
    िस
    -0.06
    採
    -0.06
     dro
    -0.06
    POSITIVE LOGITS
     slova
    0.07
     신청
    0.07
     getPosition
    0.06
    ción
    0.06
     alarak
    0.06
    lang
    0.06
     třeba
    0.06
    lanma
    0.06
     RTVF
    0.06
     있어서
    0.06
    Act Density 0.018%

    No Known Activations