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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of inner components or structures

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

    "Inner" or "Outer" followed by another word

    np_acts-logits-general · gemini-2.0-flash

    inner product or stride

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SBATCH
    -0.52
     transfieras
    -0.51
    addContainerGap
    -0.49
    sendRedirect
    -0.46
    __(/*!
    -0.45
    chieht
    -0.41
     Chwiliwch
    -0.41
    PostInfinity
    -0.40
    tagHelperRunner
    -0.40
    quelize
    -0.40
    POSITIVE LOGITS
     Inner
    1.09
    Inner
    1.05
     inner
    1.05
     INNER
    1.00
    inner
    0.98
     Outer
    0.90
    INNER
    0.87
     innermost
    0.86
    Outer
    0.84
    outer
    0.79
    Act Density 0.090%

    No Known Activations