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

    Neuronpedia

    INDEX
    Explanations

    metrics and statistics related to user engagement and satisfaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding "customers" or "clients"

    np_acts-logits-general · gemini-2.0-flash

    trusted customers and sales

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.76
    CloseOperation
    -0.55
    expandindo
    -0.52
     MonoBehaviour
    -0.52
    InputTagHelper
    -0.50
    ロウィン
    -0.50
    LabelTagHelper
    -0.49
    MethodManager
    -0.48
    الحياه
    -0.47
    AnchorStyles
    -0.47
    POSITIVE LOGITS
    Trusted
    0.41
    věd
    0.40
     successful
    0.39
    実績
    0.37
     trusted
    0.36
     successfully
    0.36
    ngdoc
    0.36
    élimin
    0.35
     éxito
    0.34
     exitos
    0.34
    Act Density 0.158%

    No Known Activations