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

    Neuronpedia

    INDEX
    Explanations

    skill and ability

    np_max-act · gemini-2.0-flash

    The neuron detects words and phrases that refer to a person’s skill, ability, or level of competence (including terms like “skill,” “ability,” “competence,” “incompetence,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     SYSTEM
    -0.07
     officer
    -0.07
     prevention
    -0.07
    (Task
    -0.07
     await
    -0.07
     consumption
    -0.06
    convert
    -0.06
    description
    -0.06
    _SECTION
    -0.06
     tender
    -0.06
    POSITIVE LOGITS
    ≠
    0.07
    plain
    0.07
    حث
    0.06
    を見る
    0.06
     �
    0.06
     Overs
    0.06
     dissatisfaction
    0.06
    /j
    0.06
     colum
    0.06
    -vers
    0.06
    Act Density 0.071%

    No Known Activations