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

    Neuronpedia

    INDEX
    Explanations

    references to people and community dynamics

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

    groups of people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lenker
    -0.50
    AnimationsModule
    -0.48
     calcetines
    -0.47
    gdx
    -0.47
     oprot
    -0.46
     poichè
    -0.46
    getMinutes
    -0.46
    AccessorTable
    -0.45
    arote
    -0.45
     presidenta
    -0.45
    POSITIVE LOGITS
    thumbsup
    0.43
    RTGC
    0.39
     West
    0.38
    ↵↵
    0.37
     Rowley
    0.37
    Medium
    0.37
    MessageWindow
    0.36
     [...]
    0.36
    dili
    0.36
    ...
    0.35
    Act Density 0.013%

    No Known Activations