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

    Neuronpedia

    INDEX
    Explanations

    data serialization/exporting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Merch
    -0.07
     โ
    -0.07
     actionPerformed
    -0.06
     projectiles
    -0.06
    SourceType
    -0.06
     inputs
    -0.06
    .ReadLine
    -0.06
    GHz
    -0.06
     load
    -0.06
    .metamodel
    -0.06
    POSITIVE LOGITS
     lends
    0.07
     چرا
    0.07
    >n
    0.06
    /up
    0.06
    (\'
    0.06
    .Ma
    0.06
     })↵
    0.06
                        ↵                    ↵
    0.06
    ');
    0.06
    】
    0.06
    Act Density 0.215%

    No Known Activations