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

    Neuronpedia

    INDEX
    Explanations

    phrases relating to the presence or absence of certain conditions or factors

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

    with or without

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     meurt
    -0.44
    appartamento
    -0.40
     proyec
    -0.38
     monasterio
    -0.38
    everything
    -0.37
    every
    -0.35
    ándola
    -0.35
     and
    -0.34
     culturelle
    -0.34
     Leidenschaft
    -0.33
    POSITIVE LOGITS
    AndEndTag
    0.90
     nonUne
    0.70
     Administrativna
    0.68
    WithIOException
    0.67
     AssemblyCompany
    0.65
     cherchés
    0.65
     ModelExpression
    0.64
     kaarangay
    0.62
    舺
    0.61
    othesis
    0.61
    Act Density 0.032%

    No Known Activations