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

    Neuronpedia

    INDEX
    Explanations

    references to internal structures or processes

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

    Follows "internal," refers to "Internal Revenue."

    np_acts-logits-general · gemini-2.0-flash

    internal Revenue

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Parcelable
    -0.79
    __':
    -0.73
     SwiftUI
    -0.71
     AssemblyCulture
    -0.70
     ControllerBase
    -0.66
    CodeAttribute
    -0.63
     navideñas
    -0.61
    ]")]
    -0.60
    __":
    -0.57
    ★★★★★
    -0.57
    POSITIVE LOGITS
     والخ
    0.69
     workings
    0.69
     combustion
    0.59
     affairs
    0.58
     Inside
    0.57
    讧
    0.55
    Inside
    0.54
     Inner
    0.53
     وخ
    0.53
    XmlAccessType
    0.53
    Act Density 0.131%

    No Known Activations