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

    Neuronpedia

    INDEX
    Explanations

    code delimiters, special characters, and newlines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ■
    1.13
    .
    1.12
     ■
    1.04
    •
    1.03
    
    0.94
    .•
    0.92
    ••
    0.91
    
    0.86
    
    0.85
     •
    0.84
    POSITIVE LOGITS
     `
    3.48
    `
    2.54
     `$
    2.54
     `.
    2.38
     (`
    2.32
     `<
    2.30
     `'
    2.28
     `#
    2.27
     `{
    2.23
     `/
    2.21
    Act Density 3.424%

    No Known Activations