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

    Neuronpedia

    INDEX
    Explanations

    negation or negative words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     చక్క
    0.41
    ရှိ
    0.40
    ಾಗಿದೆ
    0.37
    ässä
    0.37
    Yup
    0.37
    ேசு
    0.37
     clé
    0.37
     사용하여
    0.36
     చేరు
    0.36
     когда
    0.35
    POSITIVE LOGITS
     नहीं
    1.02
     neither
    1.00
     نہیں
    0.99
     Neither
    0.90
     نہیں۔
    0.90
     cannot
    0.89
     bukanlah
    0.89
    neither
    0.86
     ਨਹੀਂ
    0.86
     нельзя
    0.83
    Act Density 0.946%

    No Known Activations