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

    Neuronpedia

    INDEX
    Explanations

    grammar questions and advice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     headline
    -0.07
     vegetables
    -0.06
    169
    -0.06
     Hal
    -0.06
     VAL
    -0.06
    нути
    -0.06
     även
    -0.06
     Denmark
    -0.06
     uu
    -0.06
     dB
    -0.06
    POSITIVE LOGITS
    ictionaries
    0.08
    ()↵↵
    0.07
    act
    0.06
    Installing
    0.06
    ConnectionFactory
    0.06
    敢
    0.06
     })
↵
    0.06
    ())
↵
↵
    0.06
    笑
    0.06
     )↵↵
    0.06
    Act Density 0.090%

    No Known Activations