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

    Neuronpedia

    INDEX
    Explanations

    UI elements and controls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     не
    1.58
    Как
    1.50
     от
    1.47
    р
    1.45
    все
    1.42
    ми
    1.41
     ninguém
    1.39
     ocurrir
    1.35
     quotid
    1.33
     نړۍ
    1.33
    POSITIVE LOGITS
     plush
    1.31
    helps
    1.28
    blick
    1.26
    jButton
    1.22
    pring
    1.20
    te
    1.17
     angled
    1.16
    gfx
    1.14
    bner
    1.13
    ็ง
    1.13
    Act Density 0.128%

    No Known Activations