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

    Neuronpedia

    INDEX
    Explanations

    arrest, detention, or imprisonment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    _
    0.78
    тисти
    0.66
    "।
    0.66
    ：「
    0.66
     Inspe
    0.65
    詛
    0.65
    šte
    0.64
    りました
    0.63
    menubar
    0.63
     is
    0.62
    POSITIVE LOGITS
     imprisonment
    0.88
     incarcer
    0.84
     imprison
    0.83
     detain
    0.82
     detainees
    0.82
     detention
    0.80
     wię
    0.80
     जेल
    0.79
     arrests
    0.79
     prisons
    0.79
    Act Density 0.018%

    No Known Activations