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

    Neuronpedia

    INDEX
    Explanations

    ages

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric age mentions (e.g., “18,” “23,” “27‐year‐old,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (today
    -0.07
    pedia
    -0.07
     Evening
    -0.06
    .NewGuid
    -0.06
    Them
    -0.06
    ิท
    -0.06
    filtr
    -0.06
    Productos
    -0.06
    Keyboard
    -0.06
     Lola
    -0.06
    POSITIVE LOGITS
    =count
    0.07
     gast
    0.07
    =sub
    0.07
    、小
    0.07
    rbrace
    0.06
     predicates
    0.06
    IGGER
    0.06
    それ
    0.06
    ]*
    0.06
     agon
    0.06
    Act Density 0.065%

    No Known Activations