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

    Neuronpedia

    INDEX
    Explanations

    legal/court cases

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of court procedural outcomes or rulings, i.e. verbs like “granted,” “reversed,” and “remanded.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Debug
    -0.06
     getRandom
    -0.06
    )
↵
↵
    -0.06
     conversion
    -0.06
     Adam
    -0.06
     pagination
    -0.06
    ua
    -0.06
     inhibitor
    -0.06
     Hatch
    -0.06
     substrate
    -0.06
    POSITIVE LOGITS
     aspiring
    0.07
     Calgary
    0.07
    :pk
    0.06
     arrayWith
    0.06
    _HIDDEN
    0.06
     nem
    0.06
     Üniversit
    0.06
     heals
    0.06
    لكتر
    0.06
    ापस
    0.06
    Act Density 0.018%

    No Known Activations