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

    Neuronpedia

    INDEX
    Explanations

    references to beta and preview versions of software

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

    Pre-release software versions

    np_acts-logits-general · gemini-2.0-flash

    beta, prototype, draft

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     institución
    -0.51
     nutrición
    -0.49
     decoracion
    -0.49
    MethodManager
    -0.47
     productividad
    -0.44
     varandra
    -0.44
     sentire
    -0.44
    İstinadlar
    -0.43
     equipamiento
    -0.43
    stateProvider
    -0.43
    POSITIVE LOGITS
    draft
    0.63
    parsedMessage
    0.63
     draft
    0.62
     Draft
    0.59
     provisional
    0.59
     drafts
    0.56
     DRAFT
    0.53
    Draft
    0.53
    pushFollow
    0.53
     prototype
    0.52
    Act Density 0.399%

    No Known Activations