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

    Neuronpedia

    INDEX
    Explanations

    references to software updates and system compatibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Software updates, releases, and versions

    np_acts-logits-general · gemini-2.0-flash

    software updates and releases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.58
    LayoutStyle
    -0.57
    rungsseite
    -0.56
     مشين
    -0.50
    pion
    -0.49
    stration
    -0.49
    URIS
    -0.48
    ($__
    -0.47
    izienz
    -0.46
    wpi
    -0.45
    POSITIVE LOGITS
     updates
    1.57
     update
    1.54
     patch
    1.40
     patches
    1.29
     Updates
    1.28
    update
    1.26
     Update
    1.25
    patch
    1.23
    Patch
    1.19
     updating
    1.19
    Act Density 0.352%

    No Known Activations