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

    Neuronpedia

    INDEX
    Explanations

    sequences of non-alphanumeric, mostly hexadecimal characters, and potentially mathematical equations

    oai_token-act-pair · gemini-2.0-flash

    Code/mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kaarangay
    -1.18
    MigrationBuilder
    -1.13
    IsContent
    -1.07
    DockStyle
    -1.07
     تضيفلها
    -1.05
    LookAnd
    -1.02
     فريبيس
    -1.02
    GEBURTSDATUM
    -1.01
     виправивши
    -0.99
     Савезне
    -0.98
    POSITIVE LOGITS
     &
    0.49
     (
    0.48
    te
    0.47
    /
    0.47
     or
    0.46
     met
    0.46
    :
    0.45
     n
    0.45
    ...
    0.43
     /
    0.42
    Act Density 1.652%

    No Known Activations