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

    Neuronpedia

    INDEX
    Explanations

    show and demonstrate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     the
    0.98
    س
    0.94
    z
    0.87
    า
    0.75
     as
    0.72
    us
    0.71
     a
    0.70
     OPPO
    0.69
    to
    0.69
    ল
    0.69
    POSITIVE LOGITS
    ப்பட்டுள்ளது
    0.66
     демонстри
    0.66
     montrent
    0.58
    agne
    0.55
     demonstrations
    0.54
     zeigen
    0.54
     démontré
    0.54
    ین
    0.53
    ymph
    0.52
     basados
    0.52
    Act Density 0.236%

    No Known Activations