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

    Neuronpedia

    INDEX
    Explanations

    events related to user interactions, specifically clicking and changing states

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

    javascript click events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused79>
    -0.98
     autorytatywna
    -0.98
    <unused28>
    -0.98
    [@BOS@]
    -0.98
    <unused68>
    -0.98
    <unused16>
    -0.98
    <unused41>
    -0.98
    <unused23>
    -0.98
    <unused3>
    -0.98
    <unused14>
    -0.98
    POSITIVE LOGITS
    click
    0.38
    ,
    0.35
     click
    0.32
     nocturno
    0.30
     poitrine
    0.30
     gitara
    0.29
    Click
    0.29
    Action
    0.28
     detención
    0.28
     However
    0.27
    Act Density 0.002%

    No Known Activations