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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to mathematical analysis and probability

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    é¥
    -0.06
    attern
    -0.06
    urch
    -0.06
    oste
    -0.06
    avian
    -0.06
    utton
    -0.06
    erde
    -0.06
    yal
    -0.06
     explo
    -0.06
    illus
    -0.06
    POSITIVE LOGITS
     superior
    0.20
    æ¯Ķ
    0.19
     beats
    0.16
     surpass
    0.16
     beat
    0.15
     better
    0.15
     Superior
    0.15
     superiority
    0.14
     beating
    0.14
     beaten
    0.14
    Act Density 0.270%

    No Known Activations