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

    Neuronpedia

    INDEX
    Explanations

    challenge

    np_max-act · gemini-2.0-flash

    This neuron detects forms of the verb “challenge” (and similar contesting/attacking terms) in legal contexts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _Work
    -0.06
     BAM
    -0.06
    UpdatedAt
    -0.06
    IMATION
    -0.06
     dataIndex
    -0.06
     expand
    -0.06
     Aero
    -0.06
     زی
    -0.06
    FPS
    -0.06
    _repo
    -0.06
    POSITIVE LOGITS
     Contrast
    0.07
    انه
    0.07
    SH
    0.06
    -shell
    0.06
     powerless
    0.06
    HB
    0.06
     lesion
    0.06
    919
    0.06
     Laundry
    0.06
     يح
    0.06
    Act Density 0.004%

    No Known Activations