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

    Neuronpedia

    INDEX
    Explanations

    criminal acts and penalties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     subtle
    0.45
     XML
    0.40
     debug
    0.39
     ঘরের
    0.38
     Küh
    0.38
     Münster
    0.38
     Ruta
    0.38
     Workbench
    0.38
     perlu
    0.38
     needed
    0.38
    POSITIVE LOGITS
    criminal
    0.93
     criminal
    0.91
    Criminal
    0.85
     आपराधिक
    0.83
     CRIMINAL
    0.82
     prosecutions
    0.81
    刑事
    0.80
    犯罪
    0.79
     criminally
    0.76
     prosecution
    0.76
    Act Density 0.194%

    No Known Activations