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

    Neuronpedia

    INDEX
    Explanations

    character attributes or qualities related to hierarchies or structures in various contexts

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

    foreign languages and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     '\\;'
    -0.62
     onCreateView
    -0.61
     ujednoznacz
    -0.58
     intStringLen
    -0.58
    قایناق‌لار
    -0.57
     EconPapers
    -0.56
     ddelweddau
    -0.54
    帖最后由
    -0.53
     CURIAM
    -0.52
    TintMode
    -0.51
    POSITIVE LOGITS
    <bos>
    0.44
    ưới
    0.42
    My
    0.37
                                
    0.37
     döv
    0.36
                            
    0.35
     Administrativna
    0.35
    Into
    0.35
                                   
    0.34
    Herzliche
    0.34
    Act Density 0.019%

    No Known Activations