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

    Neuronpedia

    INDEX
    Explanations

    so far

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    现在
    0.69
     suddenly
    0.67
    如今
    0.66
     nowadays
    0.64
     now
    0.63
     eventually
    0.62
     plötzlich
    0.60
     mittlerweile
    0.60
     이제
    0.59
     ahora
    0.59
    POSITIVE LOGITS
     mostly
    0.52
    Mostly
    0.50
     Mostly
    0.50
    mostly
    0.49
     único
    0.48
     only
    0.45
     seuls
    0.45
     unsuccessful
    0.45
    只限
    0.44
    only
    0.43
    Act Density 0.005%

    No Known Activations