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

    Neuronpedia

    INDEX
    Explanations

    mathematical proofs and optimizations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TAM
    0.41
     वचन
    0.40
    chied
    0.40
     eres
    0.39
     πολλ
    0.39
     versions
    0.38
     Versions
    0.38
    versions
    0.38
     verschied
    0.38
     createNative
    0.38
    POSITIVE LOGITS
     scientifically
    0.49
     साबित
    0.47
     mathematically
    0.46
    原理
    0.45
    Optimal
    0.45
     theoretically
    0.44
     scientific
    0.44
    证明
    0.43
     theoretical
    0.43
     qualsiasi
    0.43
    Act Density 0.008%

    No Known Activations