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

    Neuronpedia

    INDEX
    Explanations

    hexadecimal numbers and their possible variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    numbers and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -0.90
    OGND
    -0.90
    httphttps
    -0.89
    Geplaatst
    -0.84
    Tembelea
    -0.83
    AddTagHelper
    -0.82
    <unused52>
    -0.81
    <unused68>
    -0.81
    <unused16>
    -0.81
    <unused8>
    -0.81
    POSITIVE LOGITS
    ↵↵
    0.48
     [*]
    0.42
    ↵
    0.39
    But
    0.38
    The
    0.38
    A
    0.37
    </blockquote>
    0.35
     But
    0.35
    I
    0.35
    1
    0.35
    Act Density 0.002%

    No Known Activations