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

    Neuronpedia

    INDEX
    Explanations

    geographical entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    人了
    0.39
     originating
    0.38
     ώστε
    0.38
     ဖြစ်
    0.37
     puedas
    0.37
    不同的
    0.36
     mức
    0.36
    >∈</
    0.36
     ItemStack
    0.36
     Jacobian
    0.35
    POSITIVE LOGITS
    ،
    0.49
    ;
    0.43
    przy
    0.42
    also
    0.42
     —
    0.41
    انے
    0.41
    пла
    0.41
    аны
    0.41
    ؛
    0.41
    ้า
    0.39
    Act Density 0.085%

    No Known Activations