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

    Neuronpedia

    INDEX
    Explanations

    the word "resulting"

    oai_token-act-pair · gemini-2.0-flash

    resulting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     <
    -0.73
     couver
    -0.71
    ATELY
    -0.71
    améli
    -0.64
    帖最后由
    -0.63
    ERVE
    -0.63
    issau
    -0.62
     transparencia
    -0.60
    ENTLY
    -0.60
     Stelle
    -0.59
    POSITIVE LOGITS
     ―――――
    1.05
     Efq
    0.99
    ſelf
    0.95
     ་་
    0.89
     itſelf
    0.88
     myſelf
    0.86
     **/
    0.84
     Shakspeare
    0.82
    ’”
    0.81
    .",
    0.80
    Act Density 3.487%

    No Known Activations