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

    Neuronpedia

    INDEX
    Explanations

    patterns and repetitions in the document structure or formatting

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

    "Un" prefix, or code/technical language

    np_acts-logits-general · gemini-2.0-flash

    image description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sizeCache
    -0.89
    tagHelperRunner
    -0.76
    OGND
    -0.74
    ConstraintMaker
    -0.74
     Taktlose
    -0.74
     ब्रेकडाउन
    -0.73
    RTEE
    -0.72
    Хьажоргаш
    -0.71
    +:+
    -0.71
    Personendaten
    -0.71
    POSITIVE LOGITS
    Medium
    0.43
    Tra
    0.40
    Array
    0.40
    Images
    0.38
    Description
    0.38
    transQ
    0.38
     Medium
    0.38
    Share
    0.38
    ifo
    0.38
     grace
    0.37
    Act Density 0.366%

    No Known Activations