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

    Neuronpedia

    INDEX
    Explanations

    density, horizontal, infant

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    able
    1.59
    uje
    1.55
     utama
    1.48
    uct
    1.47
    uction
    1.47
    izes
    1.45
    se
    1.44
    𝑮
    1.41
    ку
    1.38
    LY
    1.38
    POSITIVE LOGITS
    ي
    1.96
    ري
    1.69
    から
    1.60
    ি
    1.55
    ف
    1.53
    ৭
    1.53
     Söz
    1.46
    atown
    1.45
    ट
    1.44
    Ս
    1.44
    Act Density 0.000%

    No Known Activations