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

    Neuronpedia

    INDEX
    Explanations

    words related to being able to withstand something, or knowledge of something

    oai_token-act-pair · gemini-2.0-flash

    tolerance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     متعلقه
    -0.98
    :✨
    -0.91
    tvguidetime
    -0.90
     InputDecoration
    -0.89
     مرئيه
    -0.85
     viewDidLoad
    -0.84
    +:+
    -0.84
    ^(@)
    -0.83
    ]),
    -0.82
    XmlAccessType
    -0.82
    POSITIVE LOGITS
    <bos>
    2.11
    ↵↵
    1.16
    ↵
    1.00
    ’
    0.87
    '
    0.83
    1
    0.81
    A
    0.76
     
    0.74
    2
    0.73
    s
    0.68
    Act Density 1.458%

    No Known Activations