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

    Neuronpedia

    INDEX
    Explanations

    code components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     встроен
    0.85
     Bibliography
    0.80
     backcountry
    0.79
     gì
    0.78
     bibliography
    0.78
     inroads
    0.77
    !),
    0.77
    බැ
    0.77
    ?),
    0.76
     SRM
    0.75
    POSITIVE LOGITS
    .*;
    1.00
    able
    0.95
    ables
    0.91
    ability
    0.90
    AndView
    0.84
    rection
    0.80
    ;">
    0.79
    layer
    0.79
    ivering
    0.78
    handling
    0.78
    Act Density 0.015%

    No Known Activations