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

    Neuronpedia

    INDEX
    Explanations

    privacy and links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dyl
    0.48
     protectors
    0.46
    erà
    0.45
    od
    0.44
    pa
    0.44
    porters
    0.44
    aaa
    0.44
     семей
    0.44
     penge
    0.44
    ὼ
    0.44
    POSITIVE LOGITS
     Nations
    0.45
    リンク
    0.43
    قول
    0.42
    Union
    0.42
    hatikan
    0.42
    话
    0.42
    連合
    0.41
    株式会社
    0.41
     लिंक
    0.41
     Links
    0.41
    Act Density 0.005%

    No Known Activations