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

    Neuronpedia

    INDEX
    Explanations

    references to visual concepts or descriptive language

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

    imagery and terminology

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.59
    SqlClient
    -0.56
     CURLOPT
    -0.50
    Parcelize
    -0.48
    Nid
    -0.48
    CDCl
    -0.47
     rowspan
    -0.47
     arxiv
    -0.47
    flink
    -0.46
    borderBottom
    -0.46
    POSITIVE LOGITS
     imagery
    1.73
     Imagery
    1.51
    gery
    0.77
    pography
    0.69
     symbolism
    0.64
     IMAG
    0.62
     circuitry
    0.62
     terminology
    0.60
     warfare
    0.60
    ometry
    0.60
    Act Density 0.005%

    No Known Activations