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

    Neuronpedia

    INDEX
    Explanations

    contractions, particularly of the word "do"

    oai_token-act-pair · gemini-2.0-flash

    say apostrophe words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ({
    -0.33
    ,(
    -0.32
    >({
    -0.32
    }{(
    -0.31
    INFL
    -0.31
     (<
    -0.30
    =(
    -0.30
    首
    -0.30
    endam
    -0.30
    lago
    -0.29
    POSITIVE LOGITS
    ernalia
    0.74
    oredCriteria
    0.73
     wireType
    0.69
     للمعارف
    0.68
    клопе
    0.68
    Â
    0.68
    romeda
    0.67
     â
    0.67
    optera
    0.66
     GeoNames
    0.66
    Act Density 6.573%

    No Known Activations