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

    Neuronpedia

    INDEX
    Explanations

    AI chatbot not a professional

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     non
    0.94
     (
    0.90
    0.86
     almost
    0.75
     real
    0.72
     "
    0.72
     high
    0.69
     all
    0.68
     not
    0.67
     t
    0.67
    POSITIVE LOGITS
    📨
    1.26
    ❕
    1.26
    .)..
    1.18
    .`);
    1.18
    .??
    1.14
    💠
    1.14
    .​​
    1.14
    <unused1408>
    1.13
    🔉
    1.13
    。...
    1.12
    Act Density 0.102%

    No Known Activations