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

    Neuronpedia

    INDEX
    Explanations

    modal verbs that express possibility or obligation

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

    would cause or enable actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCompany
    -0.69
    BufferException
    -0.59
    MemoryWarning
    -0.50
    styleType
    -0.48
    zionalità
    -0.48
     getLayout
    -0.47
    期刊论文
    -0.47
    majánló
    -0.47
     HomeController
    -0.47
     houſe
    -0.46
    POSITIVE LOGITS
     helps
    0.55
     permitan
    0.53
     help
    0.50
     enables
    0.46
     enable
    0.46
     permita
    0.46
     ļ
    0.42
     promote
    0.41
     ayud
    0.40
     increase
    0.40
    Act Density 0.216%

    No Known Activations