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

    Neuronpedia

    INDEX
    Explanations

    specific programming commands or function calls

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

    programming code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCompany
    -0.69
     queſta
    -0.64
    MLLoader
    -0.63
     MainAxisSize
    -0.63
     /\.(
    -0.62
    +#+#
    -0.61
    LLocation
    -0.60
    eload
    -0.58
    +#+
    -0.57
     indígen
    -0.56
    POSITIVE LOGITS
     nahilalakip
    0.46
    /******/
    0.40
     يتيمه
    0.36
    ，
    0.35
        
    0.34
    \[
    0.34
            
    0.34
    Princeton
    0.33
                        
    0.33
    0.33
    Act Density 0.026%

    No Known Activations