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

    Neuronpedia

    INDEX
    Explanations

    not impossible

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    classroom
    0.50
    Collective
    0.48
    blast
    0.48
    collective
    0.47
    दी
    0.47
    advance
    0.47
    inception
    0.46
    របស់យើង
    0.46
    다음
    0.46
    룰
    0.46
    POSITIVE LOGITS
     Ordering
    0.47
     splitting
    0.46
     ordering
    0.46
     LEDs
    0.45
     Mono
    0.45
     uric
    0.42
     separating
    0.41
     MOQ
    0.41
     Google
    0.41
     repulsive
    0.40
    Act Density 0.001%

    No Known Activations