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

    Neuronpedia

    INDEX
    Explanations

    code examples and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     பதவி
    0.12
     deciding
    0.11
    atini
    0.10
    นาย
    0.10
    año
    0.10
    జ
    0.10
    纭
    0.10
    JSON
    0.10
    Serial
    0.10
     phát
    0.09
    POSITIVE LOGITS
     olmayan
    0.12
    Gradient
    0.11
     Rim
    0.11
    渐
    0.11
     μέρος
    0.11
     Rimini
    0.10
     mix
    0.10
     বৈ
    0.10
    碑
    0.10
    ▽
    0.10
    Act Density 0.004%

    No Known Activations