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

    Neuronpedia

    INDEX
    Explanations

    blank spaces or indentation in the text

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

    program code, citations, and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الرياضيه
    -0.91
    StoryboardSegue
    -0.82
     verſ
    -0.81
     ſch
    -0.78
     queſta
    -0.75
     ſche
    -0.73
     Reſ
    -0.73
    ⓧ
    -0.72
     мәкал
    -0.72
    ftagPool
    -0.71
    POSITIVE LOGITS
    So
    0.38
    
    0.36
    Hello
    0.35
    0.33
    My
    0.31
    ↵
    0.31
    CppMethod
    0.31
    ...
    0.30
    ↵↵↵
    0.29
        
    0.29
    Act Density 0.014%

    No Known Activations