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

    Neuronpedia

    INDEX
    Explanations

    biography, French Quarter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    െയി
    0.48
    อป
    0.45
    Monthly
    0.44
    Piano
    0.44
    Mockito
    0.42
    く
    0.42
    ibilities
    0.41
    ือ
    0.41
    риф
    0.41
    зим
    0.41
    POSITIVE LOGITS
     explotación
    0.46
     Giáo
    0.41
     මෙය
    0.41
     ভেতর
    0.41
     temprana
    0.41
     আপনাদের
    0.40
     வழியாக
    0.40
     Cruz
    0.40
     tất
    0.40
     giáo
    0.39
    Act Density 0.001%

    No Known Activations