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

    Neuronpedia

    INDEX
    Explanations

    ```php` blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     marinated
    0.43
     ediyor
    0.41
    요일
    0.41
     Caledonia
    0.40
     standen
    0.39
     tunique
    0.38
     mustn
    0.38
     sweetened
    0.38
    ***",
    0.38
    ｍｍ
    0.38
    POSITIVE LOGITS
     ${\
    1.00
     {\
    0.95
     {"
    0.93
     {'
    0.88
    {\
    0.85
    ${\
    0.83
     {@
    0.80
     【
    0.72
    {"
    0.71
    ({'
    0.71
    Act Density 0.002%

    No Known Activations