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

    Neuronpedia

    INDEX
    Explanations

    rhetorical audience writing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    อย่า
    0.59
    ocarp
    0.53
    tropical
    0.49
    市场上
    0.48
    ্টো
    0.48
     undoubtedly
    0.48
    ोक
    0.48
     निरीक्षक
    0.48
    о
    0.48
    mango
    0.47
    POSITIVE LOGITS
    ত্যার
    0.59
     novembro
    0.57
     St
    0.55
    bloc
    0.53
     Writers
    0.52
     Erfurt
    0.52
     março
    0.51
     Règles
    0.51
    ኽ
    0.51
     Aralık
    0.50
    Act Density 0.023%

    No Known Activations