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

    Neuronpedia

    INDEX
    Explanations

    Off-target effects

    np_max-act · gemini-2.0-flash

    The neuron detects hyphenated technical terms that flag undesirable or erroneous effects—e.g. “off-target” or “non-specific.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     farms
    -0.07
     SDK
    -0.07
     plugs
    -0.06
    invoices
    -0.06
    artner
    -0.06
    ку
    -0.06
    -0.06
    سنگ
    -0.06
    uropean
    -0.06
    useState
    -0.06
    POSITIVE LOGITS
     Phantom
    0.08
    .damage
    0.08
    º
    0.07
    .mapbox
    0.07
     апреля
    0.07
     assure
    0.07
     getPassword
    0.06
    \R
    0.06
    iž
    0.06
     Kasich
    0.06
    Act Density 0.023%

    No Known Activations