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

    Neuronpedia

    INDEX
    Explanations

    parsing web pages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iterable
    0.38
     enclosing
    0.37
     обсу
    0.36
     наси
    0.36
    சரி
    0.36
     சரி
    0.35
     canciones
    0.35
     ടെ
    0.35
    iding
    0.34
    iper
    0.34
    POSITIVE LOGITS
    υκ
    0.40
     greatness
    0.38
     steam
    0.38
     makers
    0.37
     features
    0.37
    javascript
    0.37
     JavaScript
    0.37
     Steam
    0.36
    ኞች
    0.36
     মৃদু
    0.36
    Act Density 0.001%

    No Known Activations