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

    Neuronpedia

    INDEX
    Explanations

    institutions and confinement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     veste
    0.62
     അദ്ദേഹ
    0.62
    ção
    0.60
    ുടെ
    0.59
    อนไลน์
    0.58
     ಅವರ
    0.58
     visão
    0.57
     นาย
    0.56
    aseña
    0.55
    ต์
    0.55
    POSITIVE LOGITS
     prisons
    0.91
     Prison
    0.90
     prison
    0.90
    Hospital
    0.86
     hospitals
    0.85
     Hospital
    0.84
     hospitales
    0.81
     hospital
    0.78
    Prison
    0.78
     psychiatric
    0.77
    Act Density 0.049%

    No Known Activations