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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions

    np_max-act · gemini-2.0-flash

    The neuron flags descriptive adjectives of material or functional properties—especially those ending in “-ive,” “-able,” or “-ible.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Will
    -0.07
     will
    -0.06
    JAVA
    -0.06
    。\
    -0.06
    OH
    -0.06
     reported
    -0.06
     prescribing
    -0.06
     fists
    -0.06
    .LENGTH
    -0.06
     benches
    -0.06
    POSITIVE LOGITS
     humorous
    0.07
     dòng
    0.07
     Atmos
    0.06
     الجم
    0.06
     hindsight
    0.06
    _Runtime
    0.06
    Cancelled
    0.06
     handleSubmit
    0.06
    赛
    0.06
    WebResponse
    0.06
    Act Density 0.409%

    No Known Activations