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

    Neuronpedia

    INDEX
    Explanations

    technical terms and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     महत्त्वा
    0.49
    ؕ
    0.49
    وْ
    0.48
     태
    0.45
    syntax
    0.44
    ரும்பு
    0.44
    ⴷ
    0.43
    ोक
    0.43
     viser
    0.42
    байд
    0.42
    POSITIVE LOGITS
    iori
    0.50
    iami
    0.49
     উদ্দীপ
    0.48
    箱
    0.47
     applic
    0.47
     exchanges
    0.46
    使用
    0.46
     hipótesis
    0.46
     petting
    0.45
    中
    0.45
    Act Density 0.000%

    No Known Activations