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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on terms used in chemical‐industry write-ups—particularly mentions of specific compounds, materials, and their physical or structural descriptions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Bag
    -0.07
    ega
    -0.07
    Sugar
    -0.06
    ноз
    -0.06
     Hudson
    -0.06
    بلغ
    -0.06
    Wire
    -0.06
    Len
    -0.06
    ่าง
    -0.06
    Aggregate
    -0.06
    POSITIVE LOGITS
     nokt
    0.06
    _CHILD
    0.06
     injustice
    0.06
    _ELEMENT
    0.06
     Nordic
    0.06
    ()?
    0.06
     Notices
    0.06
    "--
    0.06
     Social
    0.05
    :void
    0.05
    Act Density 0.229%

    No Known Activations