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

    Neuronpedia

    INDEX
    Explanations

    words associated with legal proceedings and testimonies

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -3.61
    '
    -0.92
    ’
    -0.84
    The
    -0.70
    ↵
    -0.65
    <h2>
    -0.64
     the
    -0.63
    “
    -0.59
    "
    -0.57
    I
    -0.57
    POSITIVE LOGITS
    orative
    0.60
    xffffffff
    0.58
     Strap
    0.55
    λαν
    0.54
    ourite
    0.54
    stanza
    0.54
    󠁢
    0.54
    geries
    0.53
    ophone
    0.53
     ويكيپ
    0.53
    Act Density 39.004%

    No Known Activations