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

    Neuronpedia

    INDEX
    Explanations

    the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     состоится
    0.41
     ப
    0.37
     сложи
    0.37
    Ė
    0.37
    arnataka
    0.37
     대로
    0.36
     주어진
    0.36
    barui
    0.36
     circun
    0.35
    ಾನ
    0.35
    POSITIVE LOGITS
     menus
    0.39
     behavior
    0.38
     theses
    0.38
     বেশিরভাগ
    0.38
     has
    0.38
     zir
    0.38
     escond
    0.38
     fingerprints
    0.38
     tedav
    0.38
     constamment
    0.38
    Act Density 0.041%

    No Known Activations