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

    Neuronpedia

    INDEX
    Explanations

    solidity, programming language, code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     என்ன
    0.37
     टेबलेट
    0.37
     चुनने
    0.36
     perso
    0.36
     brochures
    0.36
     पढ़ाने
    0.36
     따라
    0.35
    ທີ
    0.35
     दश
    0.35
    壓縮
    0.35
    POSITIVE LOGITS
    Relevant
    0.39
     خاط
    0.36
    Big
    0.35
    relevant
    0.35
    水平
    0.35
    мая
    0.35
    さを
    0.35
     localVarAccept
    0.34
     リング
    0.33
    onej
    0.33
    Act Density 0.000%

    No Known Activations