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

    Neuronpedia

    INDEX
    Explanations

    words that indicate a description and analysis of data, numbers, statistics, work and information

    oai_token-act-pair · gemini-2.0-flash

    verbs indicating existence or occurrence

    np_token-act-pair-logits · gpt-4o-mini

    statements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AntiForgeryToken
    -0.68
     include
    -0.63
     INCLUDE
    -0.61
     Include
    -0.61
    complexContent
    -0.60
    jooq
    -0.57
     CURIAM
    -0.56
    roek
    -0.54
    ſelves
    -0.54
     Theſe
    -0.53
    POSITIVE LOGITS
     is
    0.78
     has
    0.61
     occurs
    0.59
     converges
    0.57
     happens
    0.56
    Portail
    0.56
     exists
    0.56
     avviene
    0.56
     revolves
    0.54
     intersects
    0.54
    Act Density 7.418%

    No Known Activations