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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and the context around them

    oai_token-act-pair · gemini-2.0-flash

    science and math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -2.06
    ↵↵
    -0.98
    '
    -0.76
    ’
    -0.71
    ش
    -0.49
    D
    -0.49
    ‘
    -0.48
    N
    -0.47
    ال
    -0.45
     and
    -0.45
    POSITIVE LOGITS
     CreateTagHelper
    1.16
    enumi
    1.16
     EconPapers
    1.14
    AddTagHelper
    1.05
    WebVitals
    1.00
    AndEndTag
    0.95
     مشين
    0.94
     Normdatei
    0.93
    MemoryWarning
    0.93
    ReusableCell
    0.92
    Act Density 6.579%

    No Known Activations