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

    Neuronpedia

    INDEX
    Explanations

    definitions and calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     spaceShip
    0.41
     життя
    0.39
    সজ্জিত
    0.39
    ionista
    0.39
    він
    0.38
     języ
    0.38
     tiếng
    0.36
    msgSender
    0.36
     playerCount
    0.35
     imageHeight
    0.35
    POSITIVE LOGITS
    ═
    0.42
     வருக
    0.41
     وتق
    0.41
    :
    0.40
    وا
    0.37
     viens
    0.37
    \
    0.36
     rész
    0.36
    0.36
    semos
    0.35
    Act Density 0.001%

    No Known Activations