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

    Neuronpedia

    INDEX
    Explanations

    the presence of structural elements and formatting in text

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

    Preceding math symbols or special characters

    np_acts-logits-general · gemini-2.0-flash

    mathematical symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    os
    -0.55
     
    -0.52
     N
    -0.49
    lar
    -0.49
    un
    -0.49
     L
    -0.47
     Gra
    -0.46
     Qu
    -0.46
     Ma
    -0.45
    ์
    -0.45
    POSITIVE LOGITS
     Shakspeare
    1.09
    ImageContext
    1.01
     utafitiHapana
    1.01
    WebVitals
    1.01
    AccessorTable
    0.95
    GEBURTSDATUM
    0.93
     Monfieur
    0.92
    XmlAccessorType
    0.91
     Cæsar
    0.91
     Audiodateien
    0.91
    Act Density 0.103%

    No Known Activations