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

    Neuronpedia

    INDEX
    Explanations

    expressions of happiness, satisfaction, and being impressed

    oai_token-act-pair · gemini-2.0-flash

    say "with"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sizeCache
    -0.70
     okuyayım
    -0.69
    TagMode
    -0.67
    ThroughAttribute
    -0.64
    Дереккөздер
    -0.62
     تانيه
    -0.62
    GEBURTSDATUM
    -0.62
    ⓧ
    -0.61
    帖最后由
    -0.60
    usercontent
    -0.59
    POSITIVE LOGITS
     with
    0.76
    with
    0.50
     initComponents
    0.49
     Wiktionnaire
    0.48
    iyle
    0.48
    +#+
    0.46
    原始内容存档于
    0.45
     Your
    0.44
     dengan
    0.42
     avec
    0.41
    Act Density 0.587%

    No Known Activations