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

    Neuronpedia

    INDEX
    Explanations

    approximations, comments, or technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0
    0.90
     overcame
    0.76
    ৩৩
    0.75
    ماً
    0.74
    ما
    0.73
    ২১
    0.73
    ↵
    0.70
    ২৮
    0.68
    ০
    0.68
     Biss
    0.67
    POSITIVE LOGITS
    спи
    0.64
    ACT
    0.55
    рів
    0.55
    те
    0.54
     রওনা
    0.54
    ాయ
    0.54
    인가
    0.53
    ющим
    0.53
    ёл
    0.52
    ющий
    0.52
    Act Density 0.561%

    No Known Activations