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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to initiating actions or processes

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

    getting started

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    //
    -0.44
    devamını
    -0.42
    MockMvc
    -0.41
    лтемелер
    -0.40
    BufferException
    -0.38
    tanleria
    -0.37
    diali
    -0.36
     Wey
    -0.36
     ويكيميديا
    -0.36
     Chwiliwch
    -0.35
    POSITIVE LOGITS
     Started
    0.65
    Started
    0.58
     Starter
    0.52
    Starter
    0.51
    started
    0.51
     onboarding
    0.49
    入门
    0.48
    Beginner
    0.47
    STARTED
    0.47
    starter
    0.47
    Act Density 0.004%

    No Known Activations