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

    Neuronpedia

    INDEX
    Explanations

    medical or chemical terms, often with prefixes or suffixes.

    oai_token-act-pair · gemini-2.0-flash

    say "m" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     m
    -0.90
     M
    -0.88
     MAM
    -0.81
     getM
    -0.81
     MM
    -0.81
     MEN
    -0.78
     MA
    -0.77
     ma
    -0.77
     MAN
    -0.77
     М
    -0.75
    POSITIVE LOGITS
    AddTagHelper
    0.79
    RenderAtEndOf
    0.64
    BarStyle
    0.63
    хьтан
    0.51
    Dichlorobenzene
    0.50
    {~
    0.49
    mice
    0.48
    ValueStyle
    0.47
    mités
    0.46
    EnableWeb
    0.46
    Act Density 8.038%

    No Known Activations