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

    Neuronpedia

    INDEX
    Explanations

    gain or maintain control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Accessible
    0.39
    Controlled
    0.36
     dostępne
    0.35
     Accessible
    0.35
    aconit
    0.34
     authentically
    0.33
    accessible
    0.33
     accessibles
    0.33
     accesible
    0.33
     Properly
    0.33
    POSITIVE LOGITS
     ownership
    0.95
     dominion
    0.82
     control
    0.81
    ownership
    0.75
     permission
    0.74
     custody
    0.73
     autonomy
    0.71
     possession
    0.68
     authority
    0.68
     jurisdiction
    0.68
    Act Density 0.083%

    No Known Activations