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

    Neuronpedia

    INDEX
    Explanations

    three sets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     \""
    1.28
     `--
    1.26
     (`
    1.23
     `
    1.22
    ･･･
    1.20
    ･･
    1.19
    {\'
    1.18
    `:
    1.12
     `'
    1.12
    ":
    1.09
    POSITIVE LOGITS
    
    1.62
    ‼️
    1.22
     🥰
    1.22
    🥺
    1.18
    ⁩
    1.16
    🥰
    1.15
     😂😂
    1.14
    ‌
    1.14
     ❤️
    1.14
    ️
    1.11
    Act Density 0.030%

    No Known Activations