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

    Neuronpedia

    INDEX
    Explanations

    ARM, Honda, armor, or base related terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﺀ
    1.21
    ️⃣
    1.17
    ه
    1.15
    ش
    1.13
    ี
    1.10
    ，
    1.09
    ah
    1.08
    ১২
    1.07
    ين
    1.06
    ⃣
    1.05
    POSITIVE LOGITS
    s
    1.34
    lodash
    1.01
    และการ
    1.00
    ुणा
    0.91
    sdf
    0.91
     रोकने
    0.91
    ்கலை
    0.90
    餬
    0.90
    ים
    0.89
    nake
    0.89
    Act Density 0.000%

    No Known Activations