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

    Neuronpedia

    INDEX
    Explanations

    a variety of items in different short documents

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    enumii
    -0.90
    abestanden
    -0.84
    interopRequire
    -0.82
    LookAnd
    -0.77
    IntoConstraints
    -0.77
    期刊论文
    -0.76
     Roskov
    -0.75
    曖昧さ回避
    -0.72
     OFDb
    -0.70
    DeleteBehavior
    -0.70
    POSITIVE LOGITS
    <bos>
    1.30
    '
    0.69
    ↵
    0.68
    ↵↵
    0.63
    The
    0.61
    I
    0.51
    ’
    0.45
    This
    0.45
    With
    0.44
    We
    0.43
    Act Density 6.641%

    No Known Activations