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

    Neuronpedia

    INDEX
    Explanations

    danger and danger

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    microsoft
    0.54
    靴
    0.51
    priority
    0.50
    ිනි
    0.49
    Altri
    0.49
    有利
    0.45
    т
    0.45
    ли
    0.44
     найти
    0.44
    ticket
    0.44
    POSITIVE LOGITS
     প্রথমবারের
    0.44
     festivities
    0.44
     expressive
    0.42
    ඩ්
    0.42
     appropriateness
    0.41
    វត្ត
    0.40
     repertoire
    0.39
     oportunidade
    0.39
    NewDecoder
    0.38
     idő
    0.38
    Act Density 0.006%

    No Known Activations