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

    Neuronpedia

    INDEX
    Explanations

    disinformation and misinformation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    北海道
    0.54
    сного
    0.53
    家族
    0.51
     homozyg
    0.51
    льного
    0.51
     recorrido
    0.50
    ገል
    0.50
    त्ति
    0.48
    夗
    0.47
     pregnancies
    0.47
    POSITIVE LOGITS
     disinformation
    0.73
     you
    0.64
    filtering
    0.64
     Propaganda
    0.61
     misinformation
    0.61
    we
    0.59
     propaganda
    0.59
     your
    0.58
     countermeasures
    0.58
     Markt
    0.57
    Act Density 0.093%

    No Known Activations