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

    Neuronpedia

    INDEX
    Explanations

    elements of code structure, particularly class and method declarations

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

    code syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pinulongan
    -1.02
    <unused41>
    -0.91
    <unused14>
    -0.91
    <unused8>
    -0.90
    <unused74>
    -0.90
    <unused28>
    -0.90
    <unused68>
    -0.90
    <unused52>
    -0.90
    <unused16>
    -0.90
    <unused23>
    -0.90
    POSITIVE LOGITS
     Act
    0.30
     i
    0.30
     L
    0.29
    ,
    0.29
     val
    0.29
    之
    0.29
     Val
    0.29
     can
    0.28
    An
    0.28
     一
    0.28
    Act Density 0.010%

    No Known Activations