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

    Neuronpedia

    INDEX
    Explanations

    looking forward to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ଝ
    0.41
    ಿದ್ದರು
    0.40
     genes
    0.39
     puedes
    0.39
     obsah
    0.39
     millimeters
    0.39
     filled
    0.38
    थी
    0.38
     touchscreen
    0.38
     चहल
    0.38
    POSITIVE LOGITS
     기대
    0.85
     будет
    0.73
     będzie
    0.69
    楽しみ
    0.68
     будут
    0.64
    到时候
    0.63
    Expect
    0.63
     expect
    0.61
     იქნება
    0.61
     será
    0.60
    Act Density 0.323%

    No Known Activations