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

    Neuronpedia

    INDEX
    Explanations

    confidence

    np_max-act · gemini-2.0-flash

    This neuron fires on numeric confidence values and percent signs (i.e. floating‐point numbers and “%” in confidence scores).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Theft
    -0.06
     originated
    -0.06
    utter
    -0.06
     YORK
    -0.06
    _NULL
    -0.06
    Placement
    -0.06
    ้ำ
    -0.06
    informatics
    -0.06
    跡
    -0.06
    rypt
    -0.06
    POSITIVE LOGITS
     Chairs
    0.06
    Cum
    0.06
     مي
    0.06
     넘
    0.06
     Jasmine
    0.06
    "=>$
    0.06
    返
    0.06
     Valor
    0.06
     }]
    0.06
    ]="
    0.06
    Act Density 0.022%

    No Known Activations