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

    Neuronpedia

    INDEX
    Explanations

    comparison or degree

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    さは
    0.32
    藹
    0.29
    ávy
    0.29
    잌
    0.29
    ską
    0.29
    ᱼ
    0.29
    alnız
    0.29
     ictal
    0.28
    📶
    0.28
    డ్‌
    0.28
    POSITIVE LOGITS
     sufficiently
    0.31
     sogen
    0.31
     definitivo
    0.30
    中使用
    0.30
     definitiva
    0.29
     convencional
    0.29
     sogenannten
    0.28
    .
    0.28
     dibujos
    0.27
     pinturas
    0.27
    Act Density 0.000%

    No Known Activations