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

    Neuronpedia

    INDEX
    Explanations

    psychological manipulation and personas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     теннис
    0.46
    ھا
    0.45
    헤
    0.44
     نە
    0.43
    0.43
     Крем
    0.41
     Hôtel
    0.41
    Tennis
    0.41
     Теннис
    0.40
    0.40
    POSITIVE LOGITS
     Command
    0.44
     command
    0.43
     communication
    0.42
     createCanvas
    0.41
     Langkah
    0.40
     mental
    0.40
     Psychological
    0.40
     communications
    0.39
     showers
    0.39
     psychological
    0.39
    Act Density 0.005%

    No Known Activations