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

    Neuronpedia

    INDEX
    Explanations

    referring to position or state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     単
    0.50
     只
    0.49
     તૈય
    0.47
    ცა
    0.46
     ஏற்க
    0.46
     첫
    0.45
    पटॉप
    0.45
     unbear
    0.44
    ខ្សែ
    0.44
     접
    0.43
    POSITIVE LOGITS
    Belgium
    0.45
    作为
    0.44
    Established
    0.42
    PRESENT
    0.41
    Paragraph
    0.41
    热情
    0.40
    0.40
    Defendant
    0.39
    North
    0.39
    نامه
    0.39
    Act Density 0.001%

    No Known Activations