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

    Neuronpedia

    INDEX
    Explanations

    we can

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    script
    1.02
     my
    0.95
    my
    0.93
     I
    0.92
     مجھے
    0.91
    군
    0.88
     me
    0.88
     svého
    0.88
     solo
    0.87
    収入
    0.85
    POSITIVE LOGITS
     ourselves
    1.75
     છીએ
    1.72
     आहोत
    1.57
     precisamos
    1.57
     我们
    1.56
    ours
    1.54
     devemos
    1.53
     tayo
    1.52
     nostri
    1.49
     usamos
    1.49
    Act Density 0.676%

    No Known Activations