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

    Neuronpedia

    INDEX
    Explanations

    actions related to user interactions with buttons and controls

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

    button click event

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused52>
    -1.15
    <unused51>
    -1.15
    <unused28>
    -1.15
    <unused43>
    -1.15
    <unused8>
    -1.15
    <pad>
    -1.15
    <unused14>
    -1.15
    <unused16>
    -1.15
    <unused68>
    -1.15
    <unused79>
    -1.15
    POSITIVE LOGITS
    ActionPerformed
    0.54
    Click
    0.43
    ButtonClick
    0.40
     actionPerformed
    0.36
     With
    0.32
    2
    0.32
    1
    0.32
     krok
    0.31
    CHAPTER
    0.31
     Monday
    0.30
    Act Density 0.001%

    No Known Activations