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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the concept of freedom or the ability to choose actions

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

    free to do actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    manera
    -0.40
     Quote
    -0.38
     accompaniment
    -0.36
     oar
    -0.35
     gost
    -0.35
    quote
    -0.35
    jsxFileName
    -0.34
     efficiency
    -0.33
    ibatkan
    -0.33
    AppComponent
    -0.33
    POSITIVE LOGITS
    free
    0.71
     freely
    0.68
    Free
    0.67
     szabad
    0.67
     libertà
    0.66
    Freedom
    0.64
    freedom
    0.64
     free
    0.64
     liberdade
    0.62
     Freedom
    0.62
    Act Density 0.011%

    No Known Activations