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

    Neuronpedia

    INDEX
    Explanations

    installing software packages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ർ
    0.90
     hace
    0.89
    ographically
    0.88
    ால்
    0.88
     часы
    0.88
    ર
    0.86
     savings
    0.85
    ೂ
    0.85
     saída
    0.84
    amp
    0.83
    POSITIVE LOGITS
    특별시
    1.13
    bücher
    1.05
    ların
    0.96
    tration
    0.93
     anului
    0.93
    دو
    0.93
    Authorities
    0.92
    Cute
    0.91
    a
    0.90
    ような
    0.89
    Act Density 0.005%

    No Known Activations