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

    Neuronpedia

    INDEX
    Explanations

    helicopter or antineutrino

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     двух
    0.75
    ições
    0.72
     estás
    0.70
     situações
    0.67
     것은
    0.66
    enças
    0.64
     Está
    0.64
     чет
    0.64
     다시
    0.64
     세상
    0.64
    POSITIVE LOGITS
    та
    1.13
    8
    1.01
    4
    0.95
    5
    0.95
    D
    0.94
    на
    0.93
    K
    0.92
    CA
    0.89
    ca
    0.88
    B
    0.88
    Act Density 0.004%

    No Known Activations