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

    Neuronpedia

    INDEX
    Explanations

    expressions related to consistency in various contexts

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

    Follows "consistent" or "consistently"

    np_acts-logits-general · gemini-2.0-flash

    regularity or lack of variation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Autoritní
    -0.56
    NameInMap
    -0.55
    Personendaten
    -0.53
    MLLoader
    -0.53
     LoginPage
    -0.52
    $_['
    -0.51
     envy
    -0.51
     onCreateView
    -0.51
    MemoryWarning
    -0.50
     informée
    -0.50
    POSITIVE LOGITS
     repeated
    0.85
     frequent
    0.84
    repeated
    0.79
     periodic
    0.77
     regular
    0.75
     Repeated
    0.75
     regularly
    0.75
     recurring
    0.72
     continuous
    0.71
    Repeated
    0.71
    Act Density 0.255%

    No Known Activations