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

    Neuronpedia

    INDEX
    Explanations

    terms related to software releases and their management

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

    software release

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    extAlignment
    -0.43
    RuleContext
    -0.36
     TMPro
    -0.35
    DS
    -0.34
     Veg
    -0.34
     Mex
    -0.33
     Chinese
    -0.33
     mut
    -0.32
    Vat
    -0.32
    Veg
    -0.32
    POSITIVE LOGITS
    releases
    0.80
     release
    0.80
    release
    0.77
     releases
    0.77
    RELEASE
    0.74
     Release
    0.70
    Releases
    0.68
    released
    0.67
     RELEASE
    0.66
     Releases
    0.66
    Act Density 0.013%

    No Known Activations