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

    Neuronpedia

    INDEX
    Explanations

    experienced after

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    њем
    0.76
    ність
    0.75
    ರುವ
    0.73
    rupción
    0.71
    ็อก
    0.71
     কয়েকটি
    0.69
     wakt
    0.69
     inflación
    0.68
    栱
    0.68
    ルの
    0.66
    POSITIVE LOGITS
     ссы
    0.84
     ממש
    0.84
    -
    0.82
     her
    0.82
     също
    0.82
     lien
    0.75
     hyst
    0.75
    ет
    0.75
     foi
    0.73
     byl
    0.72
    Act Density 0.001%

    No Known Activations