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

    Neuronpedia

    INDEX
    Explanations

    news writer bylines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wikipédia
    0.42
     readme
    0.42
     Prandtl
    0.42
    VHS
    0.41
    加工
    0.40
     README
    0.40
     vasodil
    0.39
    Readme
    0.39
     pulgadas
    0.38
    Princip
    0.38
    POSITIVE LOGITS
     reporter
    1.10
     reporters
    0.95
     correspondent
    0.95
     Correspondent
    0.91
    Reporter
    0.88
    記者
    0.88
     columnist
    0.87
     correspondents
    0.85
     Reporter
    0.84
    记者
    0.81
    Act Density 0.003%

    No Known Activations