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

    Neuronpedia

    INDEX
    Explanations

    patterns of indentation and whitespace in code or text segments

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

    code punctuation or foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.68
    CppMethod
    -0.59
    VolleyError
    -0.59
    SourceChecksum
    -0.59
    extAlignment
    -0.58
    ollectionView
    -0.58
    stdc
    -0.57
    ThroughAttribute
    -0.56
    الدراسه
    -0.54
     getItemId
    -0.54
    POSITIVE LOGITS
    -------
    0.42
     ){
    0.40
     +(
    0.35
     لئے
    0.34
     )(
    0.33
     ((
    0.33
                     
    0.33
    //--
    0.32
                                 
    0.32
     ){
    0.32
    Act Density 0.066%

    No Known Activations