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

    Neuronpedia

    INDEX
    Explanations

    technical terms and conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    値を
    0.45
     fearless
    0.42
    ificent
    0.42
     mites
    0.42
    0
    0.41
    あたり
    0.41
    Pe
    0.40
     leafy
    0.40
     bananas
    0.40
    VW
    0.40
    POSITIVE LOGITS
    regul
    0.48
    製造
    0.45
     ஏனெ
    0.45
     BufferedReader
    0.44
     উন্নত
    0.43
     fabricants
    0.43
     Sabemos
    0.43
     生成
    0.42
     регу
    0.42
     MANUFACTURING
    0.42
    Act Density 0.005%

    No Known Activations