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

    Neuronpedia

    INDEX
    Explanations

    autoremove

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    لي
    0.43
     ネ
    0.43
    ൊപ്പം
    0.42
     matière
    0.41
    ní
    0.41
    ໍາ
    0.41
    Bună
    0.41
     calcule
    0.40
    લ્ડ
    0.39
     ҳо
    0.39
    POSITIVE LOGITS
    ymmetries
    0.41
     supervised
    0.40
     throughout
    0.40
     Springs
    0.40
     damped
    0.39
     Ono
    0.38
     harmless
    0.38
    ornis
    0.38
     impacts
    0.37
     Barriers
    0.37
    Act Density 0.001%

    No Known Activations