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

    Neuronpedia

    INDEX
    Explanations

    legal consequences and punishment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    鵲
    0.73
     অতি
    0.68
     происходит
    0.66
    dynamics
    0.66
     Phoebe
    0.66
     surges
    0.65
    鹊
    0.65
     иннова
    0.63
     сверх
    0.63
     проис
    0.63
    POSITIVE LOGITS
     imprisonment
    1.62
     prisión
    1.58
     prison
    1.52
     prisons
    1.38
     imprisoned
    1.36
     incarceration
    1.35
     imprison
    1.33
     prisoners
    1.32
     jail
    1.31
     incarcerated
    1.30
    Act Density 0.405%

    No Known Activations