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

    Neuronpedia

    INDEX
    Explanations

    references to fake news and concepts related to truth and falsehood

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

    falsehoods and misrepresentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PreferredItem
    -0.53
     famí
    -0.45
    Carriera
    -0.45
    Beats
    -0.45
    الإنجليزية
    -0.44
     concur
    -0.43
     commend
    -0.41
     verlang
    -0.40
    brio
    -0.40
    Continental
    -0.40
    POSITIVE LOGITS
     tromper
    0.57
    contentLoaded
    0.56
     تضيفلها
    0.55
     errores
    0.52
     Wahrheit
    0.52
     disinformation
    0.51
     falsche
    0.50
     falsehood
    0.50
     fraudulent
    0.50
     errors
    0.50
    Act Density 0.101%

    No Known Activations