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

    Neuronpedia

    INDEX
    Explanations

    code execution and file operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     αρκε
    0.32
    ρά
    0.31
    fluss
    0.30
    烷
    0.29
    λο
    0.29
     això
    0.29
    )](
    0.29
    seye
    0.28
    padStart
    0.28
    gä
    0.28
    POSITIVE LOGITS
    anagram
    0.29
    ائو
    0.27
     निम्नलिखित
    0.27
     Nós
    0.26
     समस्त
    0.26
     Ça
    0.26
     //</
    0.26
    ंदोल
    0.25
     furious
    0.25
    निम्नलिखित
    0.25
    Act Density 0.100%

    No Known Activations