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

    Neuronpedia

    INDEX
    Explanations

    elements and topics related to censorship and content regulation in media

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

    censorship or regulation

    np_acts-logits-general · gemini-2.0-flash

    censorship and objectionable content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     []:
    -0.68
     snippetHide
    -0.56
    onViewCreated
    -0.51
    viewDidLoad
    -0.49
    internalType
    -0.49
     viewDidLoad
    -0.49
    inherits
    -0.49
     Exactos
    -0.48
    THISDAY
    -0.47
    saraba
    -0.45
    POSITIVE LOGITS
     censor
    1.22
     censorship
    1.17
     censored
    1.09
     censura
    1.01
     Cens
    0.93
    censored
    0.87
     objectionable
    0.79
    cens
    0.78
    Banned
    0.77
     censure
    0.75
    Act Density 0.391%

    No Known Activations