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

    Neuronpedia

    INDEX
    Explanations

    jail and prison

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ва
    0.66
    ")->
    0.58
    は
    0.56
    ные
    0.55
    茷
    0.55
    ່ນ
    0.53
    ﺰ
    0.53
    ный
    0.52
    ів
    0.52
    ции
    0.51
    POSITIVE LOGITS
     jail
    0.75
     prisons
    0.74
     jails
    0.73
     prisoners
    0.72
     imprisonment
    0.69
     Prison
    0.68
     inmates
    0.68
     जेल
    0.66
     incarceration
    0.66
     prison
    0.64
    Act Density 0.004%

    No Known Activations