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

    Neuronpedia

    INDEX
    Explanations

    help hotlines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    스럽
    0.40
    찌
    0.39
     लागेल
    0.39
    regulate
    0.38
    負荷
    0.37
    傭
    0.37
    odynamic
    0.36
    \|_{\
    0.36
    Generic
    0.35
    REGEX
    0.35
    POSITIVE LOGITS
     Сара
    0.37
     Sara
    0.36
     ""
    0.35
     solvent
    0.35
    सर
    0.35
     channel
    0.34
    omer
    0.34
     '
    0.34
     facile
    0.33
    சர்
    0.33
    Act Density 0.019%

    No Known Activations