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

    Neuronpedia

    INDEX
    Explanations

    words related to legal, business, and government reports that have the word "to" nearby

    oai_token-act-pair · gemini-2.0-flash

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.59
    '
    -0.51
     to
    -0.49
    ’
    -0.49
    igi
    -0.43
     The
    -0.42
     wanting
    -0.42
     souci
    -0.42
    bkz
    -0.41
     ř
    -0.40
    POSITIVE LOGITS
    IntoConstraints
    0.88
     виправивши
    0.86
    AnchorStyles
    0.83
    GraphicsUnit
    0.82
     Majefty
    0.80
     NSCoder
    0.79
     Efq
    0.78
     MessageBoxIcon
    0.77
    MessageOf
    0.76
    InstanceState
    0.75
    Act Density 9.668%

    No Known Activations