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

    Neuronpedia

    INDEX
    Explanations

    identification and attractiveness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bikini
    0.53
     службу
    0.46
     клетки
    0.46
     ही
    0.45
     மூன்று
    0.45
     შემდეგ
    0.44
    ération
    0.44
     Chlorine
    0.44
     सुनवाई
    0.44
     பெண்கள்
    0.43
    POSITIVE LOGITS
     apoyo
    0.48
     area
    0.44
     admirers
    0.43
     identification
    0.43
    vita
    0.43
     name
    0.42
     attractiveness
    0.41
     names
    0.41
     housekeeper
    0.41
    athlet
    0.40
    Act Density 0.004%

    No Known Activations