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

    Neuronpedia

    INDEX
    Explanations

    technical or programming terminologies and notations

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

    code snippets and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <
    -0.46
     Italijani
    -0.42
    <h1>
    -0.42
    import
    -0.35
     obligado
    -0.33
    <!
    -0.33
    ↵↵
    -0.33
    <h2>
    -0.33
    The
    -0.32
    package
    -0.31
    POSITIVE LOGITS
     препратки
    0.81
     كومونز
    0.79
    AndEndTag
    0.79
    fjspx
    0.79
    findpost
    0.74
     initComponents
    0.73
     виправивши
    0.71
     المعيارى
    0.69
    XmlAccessorType
    0.69
     nakalista
    0.69
    Act Density 0.393%

    No Known Activations