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

    Neuronpedia

    INDEX
    Explanations

    elements related to font formatting and specifications

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

    fontloader file paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.98
    <unused41>
    -0.97
    <unused8>
    -0.97
    <unused28>
    -0.97
    <unused43>
    -0.96
    <unused23>
    -0.96
    <unused68>
    -0.96
    <unused80>
    -0.96
    [@BOS@]
    -0.96
    <unused3>
    -0.96
    POSITIVE LOGITS
    Font
    0.72
     font
    0.69
    font
    0.69
    setFont
    0.60
    FONT
    0.57
     fonts
    0.56
     Font
    0.55
    Fonts
    0.55
     Fonts
    0.40
     FONT
    0.40
    Act Density 0.010%

    No Known Activations