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

    Neuronpedia

    INDEX
    Explanations

    disinformation and child relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ス
    0.48
    س
    0.48
    نا
    0.48
    Ка
    0.46
    葷
    0.46
     خانو
    0.46
    箅
    0.46
    Га
    0.45
    ágoras
    0.45
    サ
    0.45
    POSITIVE LOGITS
     rumours
    0.51
     unimaginable
    0.46
     Deane
    0.46
     Hiring
    0.46
    issuer
    0.45
     Darren
    0.45
     Denne
    0.45
     rumour
    0.45
     Villain
    0.45
     disinformation
    0.44
    Act Density 0.000%

    No Known Activations