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

    Neuronpedia

    INDEX
    Explanations

    diverse character sets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    」。
    0.80
     ceased
    0.80
    >`;
    0.79
    swf
    0.79
    ”:
    0.78
    :${
    0.78
     niemand
    0.77
     noir
    0.77
    >`,
    0.76
     skl
    0.76
    POSITIVE LOGITS
    Applicant
    0.75
    ักษ
    0.75
    席
    0.70
    ्ल
    0.66
    Ř
    0.66
     المللی
    0.64
     Polic
    0.64
    vyš
    0.63
     Saltar
    0.63
    թ
    0.63
    Act Density 0.071%

    No Known Activations