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

    Neuronpedia

    INDEX
    Explanations

    legal, work, disability

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is spot mentions of work or job‐related terms—especially references to positions, tasks, employment capacity, or job availability.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Li
    -0.07
    かない
    -0.07
     kHz
    -0.07
     Needless
    -0.06
    mtree
    -0.06
    Longitude
    -0.06
    Jones
    -0.06
    ethoven
    -0.06
     Li
    -0.06
     Plan
    -0.06
    POSITIVE LOGITS
    _cap
    0.07
    0.06
     recession
    0.06
     temporada
    0.06
    CONS
    0.06
    vestment
    0.06
     精
    0.06
    CLIENT
    0.06
    (itemView
    0.06
     değ
    0.06
    Act Density 0.002%
    No Known Activations