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

    Neuronpedia

    INDEX
    Explanations

    Core

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of institutional core facilities or core resource headings (e.g., “Core,” “Core B,” etc.) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ruins
    -0.07
     gen
    -0.07
    ones
    -0.07
     Benefit
    -0.06
    FUNC
    -0.06
    Pane
    -0.06
     person
    -0.06
    ænd
    -0.06
     Info
    -0.06
    _tracks
    -0.06
    POSITIVE LOGITS
    イヤ
    0.07
     kariy
    0.07
    _missing
    0.06
    WRAPPER
    0.06
     CGSizeMake
    0.06
     τό
    0.06
    _FULLSCREEN
    0.06
    REDIENT
    0.06
    -uppercase
    0.06
     ("%
    0.06
    Act Density 0.007%

    No Known Activations