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

    Neuronpedia

    INDEX
    Explanations

    criminal wrongdoing and betrayal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     HubSpot
    0.50
     standalone
    0.49
     geospatial
    0.47
     LinkedIn
    0.45
     Suite
    0.44
     online
    0.44
     UEFI
    0.44
     hybrid
    0.43
     immersive
    0.43
     bidirectional
    0.43
    POSITIVE LOGITS
     prostitutes
    0.55
     treason
    0.51
     मुकदमा
    0.51
     guerras
    0.51
     cárcel
    0.51
     muerte
    0.50
     pecados
    0.50
     traitor
    0.49
     humiliating
    0.49
     죽
    0.48
    Act Density 0.145%

    No Known Activations