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

    Neuronpedia

    INDEX
    Explanations

    references to upgrading or improvements in systems or services

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

    upgrade to newer versions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     intptr
    -0.51
    LookAnd
    -0.50
    Datuak
    -0.50
    hnia
    -0.48
    Charsets
    -0.45
    esgue
    -0.45
     persons
    -0.44
    omials
    -0.44
    TRIBUN
    -0.44
     person
    -0.43
    POSITIVE LOGITS
     upgrade
    1.91
     Upgrade
    1.76
    upgrade
    1.72
     upgrading
    1.65
     upgrades
    1.63
    Upgrade
    1.59
     Upgrades
    1.54
     upgraded
    1.52
    Upgrades
    1.48
     upgra
    1.24
    Act Density 0.007%

    No Known Activations