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

    Neuronpedia

    INDEX
    Explanations

    references to data structures or frameworks in programming contexts

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

    in-plane properties and in-frame deletion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    contact
    -0.28
    略
    -0.27
    くれて
    -0.27
     Armed
    -0.27
     provid
    -0.26
     contact
    -0.26
    โ
    -0.25
     deseo
    -0.24
    ękuję
    -0.24
     seems
    -0.23
    POSITIVE LOGITS
     '{@
    0.72
     AssemblyVersion
    0.69
     kaarangay
    0.69
     arşivlendi
    0.67
    IntoConstraints
    0.67
    Tembelea
    0.66
    hoeddwyd
    0.66
     okuyayım
    0.65
     strtok
    0.63
     autorytatywna
    0.62
    Act Density 0.001%

    No Known Activations