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

    Neuronpedia

    INDEX
    Explanations

    Formal text

    np_max-act · gemini-2.0-flash

    The neuron flags mentions of formal institutional or procedural concepts (e.g. methods, procedures, services, projects, products).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    battle
    -0.06
     GOD
    -0.06
    Battle
    -0.06
    jure
    -0.06
     SENSOR
    -0.06
    .tcp
    -0.06
    'use
    -0.06
     Tay
    -0.06
     God
    -0.06
     Meaning
    -0.06
    POSITIVE LOGITS
     Primer
    0.07
     distress
    0.07
     cabin
    0.07
    ản
    0.07
     entrepreneur
    0.06
    .buffer
    0.06
     carbs
    0.06
     cáo
    0.06
     temporarily
    0.06
     adına
    0.06
    Act Density 0.173%

    No Known Activations