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

    Neuronpedia

    INDEX
    Explanations

    the letter 's', specifically in contexts implying possession or plurality and potentially email addresses

    oai_token-act-pair · gemini-2.0-flash

    s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -1.05
    ↵↵
    -0.85
     S
    -0.71
    AutoScaleMode
    -0.65
      
    -0.63
    gebob
    -0.63
     
    -0.59
    /*
    -0.57
     E
    -0.56
    ьаж
    -0.56
    POSITIVE LOGITS
     ―――――
    1.16
     Efq
    1.09
     auffi
    1.08
     Majefty
    1.01
     myſelf
    1.00
     Theſe
    0.98
     Houſe
    0.97
     Diſ
    0.96
     $_"
    0.93
     ་་
    0.92
    Act Density 0.382%

    No Known Activations