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

    Neuronpedia

    INDEX
    Explanations

    instances of loop constructs in the code

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

    for loops and parenthesis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     his
    -0.35
    Inconvénients
    -0.32
    .
    -0.31
     виправивши
    -0.30
     options
    -0.29
     depending
    -0.27
    犹豫
    -0.27
     actionPerformed
    -0.27
    ...
    -0.27
     co
    -0.26
    POSITIVE LOGITS
    RenderAtEndOf
    1.02
     Administrativna
    0.94
    \{\\
    0.88
     autorytatywna
    0.86
     kasarigan
    0.82
    AndEndTag
    0.81
    :✨
    0.81
     queſta
    0.79
    knapp
    0.77
     nahilalakip
    0.77
    Act Density 0.008%

    No Known Activations