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

    Neuronpedia

    INDEX
    Explanations

    closing braces and parentheses in code snippets

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

    closing braces and parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -0.88
    DockStyle
    -0.84
    ſicht
    -0.81
     $_(
    -0.78
    MigrationBuilder
    -0.77
     zwiſchen
    -0.77
     パンチラ
    -0.77
    parsedMessage
    -0.76
    <unused3>
    -0.75
    <unused68>
    -0.75
    POSITIVE LOGITS
    .
    0.52
     because
    0.37
     if
    0.35
    ,
    0.33
     maybe
    0.33
     either
    0.33
     say
    0.32
     include
    0.31
    but
    0.31
    they
    0.31
    Act Density 0.044%

    No Known Activations