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

    Neuronpedia

    INDEX
    Explanations

    instances of imperative verbs or commands

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

    start of user turn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Kebijakan
    -0.52
    ⤒
    -0.45
     marinho
    -0.45
    abetes
    -0.44
    lapia
    -0.44
    urysty
    -0.42
    ifrance
    -0.41
     Seul
    -0.41
    lewood
    -0.40
     الرياضيه
    -0.40
    POSITIVE LOGITS
    <bos>
    0.78
     للاسماء
    0.69
     समीक्षाओं
    0.52
    contentLoaded
    0.51
    TagMode
    0.51
    uxxxx
    0.50
     Autorizaciones
    0.49
    ✨:
    0.48
    SourceChecksum
    0.46
    RegressionTest
    0.45
    Act Density 0.000%

    No Known Activations