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

    Neuronpedia

    INDEX
    Explanations

    names and titles associated with authority or prominent roles

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

    Capitalized proper nouns

    np_acts-logits-general · gemini-2.0-flash

    names of arrested people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DrawerToggle
    -0.66
    ukone
    -0.64
    ⎩
    -0.59
     onCancelled
    -0.57
    OGND
    -0.53
     Lana
    -0.53
     Tripp
    -0.52
    stoke
    -0.52
     Nicki
    -0.51
     utafitiHapana
    -0.51
    POSITIVE LOGITS
    Innoc
    0.67
     Godwin
    0.63
     Moses
    0.63
     Innocent
    0.62
     Comfort
    0.61
    Evans
    0.58
     Isaac
    0.58
     Joseph
    0.58
    Isaac
    0.57
    Mercy
    0.56
    Act Density 0.054%

    No Known Activations