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

    Neuronpedia

    INDEX
    Explanations

    now, bit, expression, relationship

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     වර්ග
    0.44
    צע
    0.43
     ممكن
    0.42
    copic
    0.42
     Spanien
    0.41
     rifer
    0.40
    伸縮
    0.40
    皮膚
    0.39
    )\|_{\
    0.38
    )²
    0.38
    POSITIVE LOGITS
    Planning
    0.46
    Interactive
    0.46
    And
    0.44
    Same
    0.44
    Value
    0.43
    Prompt
    0.43
    Body
    0.42
    Content
    0.42
    Equ
    0.41
    Directory
    0.41
    Act Density 0.000%

    No Known Activations