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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron activates on function names that release or deallocate resources (e.g. “free,” “clear,” “drop,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ัย
    -0.06
     Summers
    -0.06
     Hour
    -0.06
     하루
    -0.06
     Lok
    -0.06
     Room
    -0.06
    獎
    -0.06
     Fried
    -0.06
     Cafe
    -0.06
    UpdatedAt
    -0.06
    POSITIVE LOGITS
    abilit
    0.07
    CSI
    0.06
    acons
    0.06
    ควร
    0.06
     productos
    0.06
    355
    0.06
     أر
    0.06
     mism
    0.06
    ERVE
    0.06
    ô
    0.06
    Act Density 0.014%

    No Known Activations