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

    Neuronpedia

    INDEX
    Explanations

    feel free to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﻨ
    1.55
    ،
    1.47
    ों
    1.41
    s
    1.41
    ﻤ
    1.40
    Ν
    1.37
    OV
    1.33
     धरोहर
    1.31
    ের
    1.29
    OS
    1.29
    POSITIVE LOGITS
    ला
    1.29
    ت
    1.26
    iant
    1.23
     frontal
    1.17
    ше
    1.16
    ière
    1.15
    lify
    1.13
    ling
    1.07
    يي
    1.07
    ا
    1.07
    Act Density 0.000%

    No Known Activations