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

    Neuronpedia

    INDEX
    Explanations

    structural elements and syntax within programming code

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

    code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    
    -0.37
    GoogleApiClient
    -0.25
    träglich
    -0.23
    不
    -0.23
    awaiter
    -0.23
     estric
    -0.18
    Vegeu
    -0.18
     f
    -0.18
    更
    -0.17
     certificat
    -0.17
    POSITIVE LOGITS
     Италијани
    1.09
    <unused41>
    1.01
    [@BOS@]
    1.01
    <unused3>
    1.00
    <unused52>
    1.00
    <unused16>
    1.00
    <unused28>
    1.00
    <unused23>
    1.00
    <unused8>
    1.00
    <unused14>
    1.00
    Act Density 0.005%

    No Known Activations