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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating minimal or scarce conditions

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

    "little" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    little + [noun]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     متعلقه
    -0.82
     AssemblyTitle
    -0.67
    ależy
    -0.49
    googleapis
    -0.49
    thaler
    -0.49
    losures
    -0.48
    StyleSheet
    -0.47
     somehow
    -0.47
     viewDidLoad
    -0.45
    undas
    -0.45
    POSITIVE LOGITS
     else
    0.76
     جدًا
    0.70
     (<
    0.68
     except
    0.67
    styleable
    0.64
    intérêt
    0.64
     gawas
    0.63
    といって
    0.63
     chance
    0.62
     opportunity
    0.61
    Act Density 0.202%

    No Known Activations