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

    Neuronpedia

    INDEX
    Explanations

    quotation marks and assignment operators in code

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

    user / start of turn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.92
    ChildScrollView
    -0.63
    <unused79>
    -0.61
    <unused41>
    -0.61
    <unused28>
    -0.60
    <unused14>
    -0.60
    <unused42>
    -0.60
    +#+#
    -0.60
    <unused74>
    -0.60
    <pad>
    -0.60
    POSITIVE LOGITS
     "
    0.60
     “
    0.54
    ="//
    0.53
    __(/*!
    0.50
     "@
    0.50
     "..\..\
    0.48
    ]=="
    0.44
     "./
    0.44
     '
    0.43
    ="
    0.41
    Act Density 0.000%

    No Known Activations