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

    Neuronpedia

    INDEX
    Explanations

    technical vocabulary and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     curls
    0.45
     statistiques
    0.42
     statistics
    0.40
     pylori
    0.39
     queries
    0.38
     briefs
    0.38
     toegang
    0.38
     save
    0.37
    blonde
    0.37
     validation
    0.36
    POSITIVE LOGITS
     Prices
    0.39
    beni
    0.38
    家长
    0.38
    デジタル
    0.37
    Prices
    0.36
    居住
    0.36
    yani
    0.36
     बंध
    0.36
     jednost
    0.36
    主流
    0.36
    Act Density 0.002%

    No Known Activations