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

    Neuronpedia

    INDEX
    Explanations

    prison sentences and durations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⚕
    -1.00
     Incidence
    -0.84
    лаго
    -0.79
    geordnete
    -0.79
     aguja
    -0.78
     ensayos
    -0.76
     Fij
    -0.74
     horário
    -0.74
     copii
    -0.73
     regulador
    -0.73
    POSITIVE LOGITS
     sentence
    1.22
     consecutive
    1.16
     sentences
    1.05
     parola
    1.02
     incarceration
    1.00
     prison
    0.95
     mandatory
    0.95
     defendant
    0.92
     guidelines
    0.88
    secutive
    0.86
    Act Density 0.049%

    No Known Activations