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

    Neuronpedia

    INDEX
    Explanations

    state control and sponsorship

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     NavBar
    0.50
     IAM
    0.49
     திருதியை
    0.48
     enqueue
    0.48
     congruent
    0.48
     r
    0.47
    }+\
    0.47
     énon
    0.47
     Availability
    0.46
     Valves
    0.46
    POSITIVE LOGITS
    violence
    0.51
    state
    0.49
    State
    0.49
    Modelo
    0.46
    ود
    0.46
    STATE
    0.45
    Malay
    0.44
    Violence
    0.44
     state
    0.43
    owned
    0.43
    Act Density 0.016%

    No Known Activations