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

    Neuronpedia

    INDEX
    Explanations

    Okay or please

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Wow
    0.99
    Oh
    0.95
     Oh
    0.89
     oh
    0.89
     Wow
    0.88
     चलो
    0.86
     Lesson
    0.86
    Now
    0.85
     wow
    0.85
    Hmm
    0.83
    POSITIVE LOGITS
     sure
    1.11
     sûr
    0.84
     Sure
    0.83
     realizar
    0.83
    sure
    0.81
     deficits
    0.79
     sicuro
    0.78
     require
    0.76
     lỗi
    0.76
    ceptar
    0.76
    Act Density 0.149%

    No Known Activations