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

    Neuronpedia

    INDEX
    Explanations

    code syntax and configuration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    6
    1.66
    1
    1.59
    7
    1.57
    2
    1.54
    8
    1.46
    3
    1.45
    4
    1.43
    0
    1.43
    9
    1.40
     estadounidense
    1.35
    POSITIVE LOGITS
    1.23
     DataType
    1.19
     CRM
    1.08
    이면
    1.08
     tableView
    1.06
     уйный
    1.06
    1.04
     HTMLElement
    1.03
    ровкой
    1.01
     ойно
    1.00
    Act Density 0.279%

    No Known Activations