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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fetchData
    -0.07
     laat
    -0.06
    还是
    -0.06
     ให
    -0.06
     равно
    -0.06
     surrounded
    -0.06
     лиц
    -0.06
    อฟ
    -0.06
    虑
    -0.06
    (java
    -0.06
    POSITIVE LOGITS
     …↵↵
    0.07
     ()↵↵
    0.07
     Contest
    0.07
    ####↵
    0.07
    lob
    0.07
    ]);
↵
    0.06
    .Im
    0.06
     super
    0.06
    ..↵
    0.06
     concentrations
    0.06
    Act Density 0.111%

    No Known Activations