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

    Neuronpedia

    INDEX
    Explanations

    references to checkbox or radio button states in user interface components

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

    checked state assignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.88
    bootstrapcdn
    -0.75
     Geiſt
    -0.75
    <unused43>
    -0.73
    <unused41>
    -0.73
    <unused28>
    -0.73
    <unused14>
    -0.73
    <unused8>
    -0.73
    <unused3>
    -0.73
    <pad>
    -0.73
    POSITIVE LOGITS
    setChecked
    0.75
    checked
    0.73
    Checked
    0.72
    isChecked
    0.55
     checked
    0.55
     Checked
    0.52
     isChecked
    0.48
    check
    0.46
    Check
    0.44
     check
    0.44
    Act Density 0.002%

    No Known Activations