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

    Neuronpedia

    INDEX
    Explanations

    code commands and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hers
    0.76
     theme
    0.75
     few
    0.74
     share
    0.74
     button
    0.73
     follow
    0.73
     fell
    0.72
     nearby
    0.71
     nine
    0.70
     five
    0.70
    POSITIVE LOGITS
    Documentation
    0.75
    Од
    0.73
    Hashing
    0.71
    Acetyl
    0.70
    Suppress
    0.70
    Infrastructure
    0.70
    Administration
    0.69
    Macrophages
    0.69
    Bromo
    0.68
    PointerException
    0.68
    Act Density 0.009%

    No Known Activations