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

    Neuronpedia

    INDEX
    Explanations

    HTML elements and related attributes in a document

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

    HTML form elements

    np_acts-logits-general · gemini-2.0-flash

    html tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iſchen
    -1.09
     المعيارى
    -1.08
    <unused68>
    -1.07
    <unused14>
    -1.06
    <unused41>
    -1.06
    <unused8>
    -1.06
    <unused23>
    -1.06
    <unused74>
    -1.06
    [@BOS@]
    -1.05
    <unused3>
    -1.05
    POSITIVE LOGITS
    .
    0.35
     enfans
    0.31
    A
    0.28
    S
    0.27
    map
    0.26
    -
    0.26
     leçons
    0.26
    P
    0.26
     prêtres
    0.25
     değildir
    0.25
    Act Density 0.090%

    No Known Activations