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

    Neuronpedia

    INDEX
    Explanations

    structured programming elements and content management terms

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

    UI elements and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ब्रेकडाउन
    -0.92
    Tikang
    -0.69
     $_(
    -0.66
     Theſe
    -0.63
    __':
    -0.60
     للمعارف
    -0.59
     AssemblyCompany
    -0.59
    <pad>
    -0.59
    <unused28>
    -0.59
    <unused41>
    -0.59
    POSITIVE LOGITS
     instructions
    0.39
     fl
    0.38
     images
    0.37
     content
    0.37
    content
    0.36
     elements
    0.36
    Instructions
    0.35
    Content
    0.33
    images
    0.33
     children
    0.33
    Act Density 0.002%

    No Known Activations