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

    Neuronpedia

    INDEX
    Explanations

    subverting or undermining control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     потен
    0.40
     Aug
    0.39
    fs
    0.39
     Four
    0.38
     Typ
    0.38
     กี้
    0.38
     Air
    0.37
     型
    0.37
     Wheels
    0.37
     Diam
    0.36
    POSITIVE LOGITS
    队
    0.43
     espécies
    0.42
     instituições
    0.42
    coelastic
    0.41
    ໃຫ້
    0.40
    Ⴀ
    0.40
    ہوری
    0.40
    supabase
    0.39
    社会
    0.39
    ਼
    0.39
    Act Density 0.001%

    No Known Activations