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

    Neuronpedia

    INDEX
    Explanations

    opening and closing HTML or XML tags

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

    "<" character in code/text

    np_acts-logits-general · gemini-2.0-flash

    markup tags and attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -1.15
     EClass
    -0.96
    transQ
    -0.89
    BufferException
    -0.86
    featureID
    -0.86
     Италијани
    -0.86
    AsUp
    -0.86
    protoimpl
    -0.85
    ]--;
    -0.80
    QMetaType
    -0.80
    POSITIVE LOGITS
    <
    0.78
    source
    0.70
     IBOutlet
    0.59
     <
    0.56
     source
    0.51
    ;"><
    0.49
    <h2>
    0.48
     soft
    0.47
    )<
    0.45
    ><
    0.45
    Act Density 0.005%

    No Known Activations