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

    Neuronpedia

    INDEX
    Explanations

    references to user interface components and data structures in programming

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

    class and method names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    
    -0.61
    новниш
    -0.56
    AndFlush
    -0.54
    oneofs
    -0.53
     Signalez
    -0.52
     []:
    -0.47
    
    -0.47
    expandindo
    -0.46
    ">//
    -0.46
    Notae
    -0.45
    POSITIVE LOGITS
     myſelf
    0.59
     Playhouse
    0.54
    endtime
    0.52
    healthcare
    0.51
     Nationwide
    0.50
    Northeast
    0.50
     Cybersecurity
    0.50
    LikeLiked
    0.50
     onCreateView
    0.50
     Northeast
    0.49
    Act Density 0.542%

    No Known Activations