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

    Neuronpedia

    INDEX
    Explanations

    a variety of technical terms, potentially related to computer science, biology and other subjects.

    oai_token-act-pair · gemini-2.0-flash

    prepositions indicating location

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

    prepositions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Theſe
    -0.90
     Efq
    -0.78
     thoſe
    -0.73
     Beſ
    -0.72
     ſeveral
    -0.70
     becauſe
    -0.69
     itſelf
    -0.69
     leſs
    -0.68
     theſe
    -0.68
     useStyles
    -0.65
    POSITIVE LOGITS
     in
    1.16
     on
    1.13
     inside
    0.97
    在
    0.90
     at
    0.89
     within
    0.86
     behind
    0.86
     around
    0.73
     trên
    0.72
     beside
    0.71
    Act Density 6.119%

    No Known Activations