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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate legal processes or court proceedings

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

    references to legal or governmental procedures and actions

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

    redacted text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.58
    didSet
    -0.44
    haber
    -0.42
    ovsk
    -0.39
    สิน
    -0.39
    rmdir
    -0.39
    unsqueeze
    -0.38
     NavController
    -0.38
     keren
    -0.38
    zionamento
    -0.37
    POSITIVE LOGITS
    はじめに
    0.78
    rungsseite
    0.76
    tagHelperRunner
    0.75
    ValueStyle
    0.73
     cages
    0.71
     reds
    0.69
     red
    0.69
    IndentedString
    0.67
     necks
    0.65
    AddTagHelper
    0.64
    Act Density 0.287%

    No Known Activations