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

    Neuronpedia

    INDEX
    Explanations

    evolution, security, stores

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     szüks
    0.47
    णारी
    0.45
    ா
    0.44
    youth
    0.43
    幾
    0.43
    ἓ
    0.43
    ३
    0.41
    gua
    0.41
    ფორმა
    0.41
    𝘯
    0.41
    POSITIVE LOGITS
     séparation
    0.49
     صدر
    0.44
    बंग
    0.44
    ’
    0.43
     participação
    0.43
     peek
    0.42
     زی
    0.42
     observa
    0.42
     με
    0.42
     natura
    0.42
    Act Density 0.001%

    No Known Activations