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

    Neuronpedia

    INDEX
    Explanations

    asterisks and personal pronouns

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    S
    -0.54
    <eos>
    -0.53
    ·
    -0.52
    ↵↵
    -0.52
     س
    -0.50
    ,
    -0.48
     S
    -0.48
     .
    -0.47
     (
    -0.47
    .
    -0.46
    POSITIVE LOGITS
    ThroughAttribute
    0.95
     nakalista
    0.86
     resourceCulture
    0.84
     CreateTagHelper
    0.83
     متعلقه
    0.82
    GEBURTSDATUM
    0.79
     Мексичка
    0.79
    存于互联网档案馆
    0.79
    AndEndTag
    0.78
    sprzedam
    0.73
    Act Density 0.407%

    No Known Activations