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

    Neuronpedia

    INDEX
    Explanations

    academic citations and references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     당신
    0.86
     founder
    0.83
     manageable
    0.82
     quirky
    0.80
     Partnerships
    0.79
     récit
    0.78
     과정
    0.77
    issez
    0.77
     Yourself
    0.76
     learnings
    0.76
    POSITIVE LOGITS
    Jiang
    0.92
    doi
    0.88
    Zhang
    0.85
    luit
    0.83
    ASTM
    0.79
     Seo
    0.77
    National
    0.77
    Wikipedia
    0.77
    Feng
    0.76
    Wool
    0.76
    Act Density 0.038%

    No Known Activations