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

    Neuronpedia

    INDEX
    Explanations

    starting new sentences with phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ach
    0.59
    onic
    0.49
     रोटी
    0.49
    itone
    0.49
    undo
    0.47
    ack
    0.47
    name
    0.47
    og
    0.47
    und
    0.45
    ne
    0.45
    POSITIVE LOGITS
     fourn
    0.51
     ہاکی
    0.50
     posiada
    0.49
     спорттук
    0.49
     shew
    0.48
     compétition
    0.48
    秶
    0.47
     baisse
    0.47
     ⭐
    0.46
     budú
    0.46
    Act Density 0.001%

    No Known Activations