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

    Neuronpedia

    INDEX
    Explanations

    the word "shadow."

    oai_token-act-pair · gemini-2.0-flash

    shadow

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Reſ
    -1.04
     itſelf
    -1.02
     Houſe
    -0.99
     ―――――
    -0.96
     photolibrary
    -0.96
     themſelves
    -0.94
     greateſt
    -0.93
     againſt
    -0.93
     Anſ
    -0.90
     Conſ
    -0.90
    POSITIVE LOGITS
    ↵↵
    0.75
    //}
    0.62
    ')),
    0.59
     \\
    0.54
    ')[
    0.54
    "));
    0.54
     
    0.54
    ']),
    0.53
    tomation
    0.53
    '))
    0.52
    Act Density 1.170%

    No Known Activations