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

    Neuronpedia

    INDEX
    Explanations

    terms related to control systems and control signals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Архівовано
    -0.40
     nonUne
    -0.39
     Ejército
    -0.39
    PYX
    -0.39
     appunto
    -0.37
     Púb
    -0.35
     ilha
    -0.35
     extranjero
    -0.35
     irmã
    -0.34
    żdy
    -0.34
    POSITIVE LOGITS
     control
    2.02
    control
    1.92
     Control
    1.90
     CONTROL
    1.80
    Control
    1.77
    CONTROL
    1.64
     controls
    1.62
     controle
    1.56
     controll
    1.53
     contrôle
    1.52
    Act Density 0.053%

    No Known Activations