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

    Neuronpedia

    INDEX
    Explanations

    clear screen or canvas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ’),
    0.45
    oint
    0.44
    ianie
    0.44
     व्हाट
    0.43
     높아
    0.43
    what
    0.43
    imli
    0.42
    owym
    0.42
    wod
    0.42
    ianum
    0.42
    POSITIVE LOGITS
    只限平日
    0.50
     وجه
    0.49
     symmetries
    0.49
     deja
    0.48
    。
    0.47
     رسمي
    0.46
     krim
    0.46
     কৰ
    0.45
     bý
    0.44
     دين
    0.44
    Act Density 0.003%

    No Known Activations