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

    Neuronpedia

    INDEX
    Explanations

    mathematical terms and expressions related to linear algebra and algebraic geometry

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

    faces and dimensions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     three
    -0.64
     deux
    -0.64
     two
    -0.61
     zweier
    -0.60
    two
    -0.58
     trois
    -0.57
     dvou
    -0.57
    three
    -0.56
     двух
    -0.56
    Three
    -0.54
    POSITIVE LOGITS
     multi
    0.63
     Multi
    0.57
     multivariate
    0.52
     hyper
    0.50
    multi
    0.49
    Multi
    0.48
    jooq
    0.48
    encils
    0.47
    XmlEnum
    0.47
     MULTI
    0.47
    Act Density 1.144%

    No Known Activations