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

    Neuronpedia

    INDEX
    Explanations

    explaining what something is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     нескольких
    0.49
    先の
    0.49
     spowod
    0.45
    しまった
    0.44
     মনের
    0.43
     a
    0.42
     причем
    0.41
    深受
    0.41
    મના
    0.41
    然后再
    0.40
    POSITIVE LOGITS
     is
    1.05
     adalah
    0.88
     are
    0.82
     was
    0.81
     არის
    0.76
     হলো
    0.73
     ialah
    0.73
     है
    0.72
     consists
    0.72
     είναι
    0.71
    Act Density 0.014%

    No Known Activations