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

    Neuronpedia

    INDEX
    Explanations

    French personal pronouns and related words.

    oai_token-act-pair · gemini-2.0-flash

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.54
     they
    -0.51
    on
    -0.47
    j
    -0.46
    們
    -0.45
    "
    -0.44
    they
    -0.41
    we
    -0.41
    inguém
    -0.41
     们
    -0.40
    POSITIVE LOGITS
     Administrativna
    0.81
     lenker
    0.79
    ImageContext
    0.79
    DebuggerNonUser
    0.77
    expandindo
    0.77
     Normdatei
    0.76
    ArgsConstructor
    0.76
    出版年
    0.76
    UnitTesting
    0.75
    awtextra
    0.74
    Act Density 12.000%

    No Known Activations