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

    Neuronpedia

    INDEX
    Explanations

    declarative navigation and SQL comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pancreas
    0.51
    ously
    0.50
    ίου
    0.50
    apsing
    0.48
     पॉलिटी
    0.46
    <a>
    0.46
    靑
    0.46
     postulate
    0.46
     compartment
    0.45
     outperforms
    0.45
    POSITIVE LOGITS
     jeden
    0.75
     edificio
    0.65
    ș
    0.65
    L
    0.64
    ോ
    0.63
    T
    0.60
    开始
    0.59
    ONEDB
    0.58
    安徽
    0.57
    ج
    0.57
    Act Density 0.003%

    No Known Activations