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

    Neuronpedia

    INDEX
    Explanations

    code structure elements, particularly focusing on semicolons, parentheses, and block delimiters in programming syntax

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

    code returning values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Roskov
    -1.16
    <unused16>
    -1.06
    <unused41>
    -1.06
    <unused14>
    -1.06
    <unused28>
    -1.06
    [@BOS@]
    -1.06
    <unused68>
    -1.06
    <unused17>
    -1.05
    <unused8>
    -1.05
    <unused3>
    -1.05
    POSITIVE LOGITS
    …
    0.30
     slutt
    0.29
     y
    0.28
     derfor
    0.26
    ...
    0.25
      
    0.25
    ↵
    0.25
     inşa
    0.25
     …
    0.24
    frå
    0.24
    Act Density 0.013%

    No Known Activations