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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and code punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    性格
    0.44
    versive
    0.44
     অনুভূত
    0.41
     sting
    0.41
    iffer
    0.40
     hük
    0.40
    تنا
    0.40
     Detroit
    0.39
    防
    0.39
                 
    0.38
    POSITIVE LOGITS
     入っ
    0.52
    ೋತಿ
    0.50
    𝐜
    0.49
     書い
    0.48
     jarak
    0.48
     imassa
    0.47
     saddhim
    0.47
    𝙙
    0.47
    哚
    0.46
    ॉड
    0.45
    Act Density 0.000%

    No Known Activations