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

    Neuronpedia

    INDEX
    Explanations

    fusion power quality saves

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     は
    0.46
    🥥
    0.45
     kug
    0.45
     هذا
    0.45
     пові
    0.43
     shone
    0.42
    Particles
    0.42
     голу
    0.41
     هي
    0.41
     defensa
    0.41
    POSITIVE LOGITS
    Cruz
    0.41
    境
    0.39
    <0xE2>
    0.38
     promotional
    0.38
    Promotion
    0.38
    Emb
    0.38
    भार
    0.37
    Signature
    0.37
    യായ
    0.37
    السلام
    0.37
    Act Density 0.000%

    No Known Activations