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

    Neuronpedia

    INDEX
    Explanations

    references to modules and entities in programming contexts

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

    Mø depletion, pushed on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Flushing
    -0.56
     rivi
    -0.53
     Donnie
    -0.52
     Whence
    -0.52
    featureID
    -0.51
     whence
    -0.50
    SBATCH
    -0.50
     Gown
    -0.49
    gown
    -0.49
     ofici
    -0.47
    POSITIVE LOGITS
    Composable
    0.92
    jsdelivr
    0.60
     transfieras
    0.57
     viewType
    0.57
    XmlEnum
    0.56
     SwiftUI
    0.55
     שוליים
    0.54
    ंदीखरीदारी
    0.54
     isInitialized
    0.54
    Erreferentziak
    0.52
    Act Density 0.001%

    No Known Activations