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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating disinformation and criticism regarding government and media narratives

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

    Statements of untruth or falsehood

    np_acts-logits-general · gemini-2.0-flash

    untrue, false, lies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyProduct
    -0.62
    Filmografie
    -0.61
    Atsauces
    -0.53
    είο
    -0.52
     '\\;'
    -0.52
    labelledby
    -0.51
    Revenir
    -0.51
    BackStack
    -0.51
     Wicidata
    -0.51
    Portail
    -0.50
    POSITIVE LOGITS
     falsehood
    1.38
     untrue
    1.34
     lies
    1.33
     false
    1.33
     misinformation
    1.27
     lie
    1.24
     inaccurate
    1.21
    false
    1.13
     unfounded
    1.09
     fabricated
    1.08
    Act Density 0.761%

    No Known Activations