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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash

    The neuron activates on wording that states what a product is engineered or “designed for,” flagging product‐purpose or intended‐use phrases.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    oyo
    -0.07
    -proxy
    -0.06
    див
    -0.06
    Brains
    -0.06
    olving
    -0.06
     kdo
    -0.06
     lays
    -0.06
    urgent
    -0.06
    Rub
    -0.06
     下
    -0.06
    POSITIVE LOGITS
     ASN
    0.07
     milestones
    0.07
    ."+
    0.07
    .getAttribute
    0.07
    foregroundColor
    0.07
     FN
    0.07
     milestone
    0.06
     pesso
    0.06
     Czech
    0.06
    .charAt
    0.06
    Act Density 0.018%

    No Known Activations