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

    Neuronpedia

    INDEX
    Explanations

    references to methodologies and techniques in scientific contexts

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

    a "method", "strategy", or "technique"

    np_acts-logits-general · gemini-2.0-flash

    methods, techniques, and strategies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    inflammation
    -0.44
     Inflammatory
    -0.44
     Donuts
    -0.42
     inflam
    -0.41
     Charger
    -0.41
     assembling
    -0.41
    inflammatory
    -0.41
    acinth
    -0.41
     isoli
    -0.40
     HomeController
    -0.40
    POSITIVE LOGITS
     method
    0.72
     método
    0.71
    method
    0.69
     méthode
    0.69
     metodo
    0.66
     devised
    0.66
     METHOD
    0.65
     estrategia
    0.63
     methods
    0.63
    方法
    0.62
    Act Density 1.063%

    No Known Activations