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

    Neuronpedia

    INDEX
    Explanations

    legal and medical discussions of gender in discrimination cases

    oai_token-act-pair · gemini-2.0-flash

    gender

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -1.27
     purpoſe
    -1.22
     avoient
    -1.16
     myſelf
    -1.16
     itſelf
    -1.16
     himſelf
    -1.12
     Efq
    -1.12
     ſtate
    -1.11
     Monfieur
    -1.10
     whoſe
    -1.08
    POSITIVE LOGITS
     -
    0.71
    ↵↵
    0.69
    rmtree
    0.67
    <td>
    0.66
     via
    0.63
    ,
    0.59
     “
    0.55
    -
    0.55
     n
    0.54
     (
    0.54
    Act Density 1.236%

    No Known Activations