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

    Neuronpedia

    INDEX
    Explanations

    torture and interrogation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Payroll
    0.46
     payroll
    0.45
     annuity
    0.44
    ộm
    0.42
     stumpage
    0.41
     selfishness
    0.41
     agrupación
    0.41
     selfish
    0.39
     ਕਰ
    0.39
     disb
    0.39
    POSITIVE LOGITS
     torture
    1.20
     interrogation
    1.20
     interrog
    1.10
     interrogate
    1.03
     interrogated
    0.97
     detainees
    0.94
    Tort
    0.94
     tort
    0.90
    tort
    0.89
     tortured
    0.88
    Act Density 0.010%

    No Known Activations