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

    Neuronpedia

    INDEX
    Explanations

    expressions related to freedom and choice in various contexts

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

    feel free to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setVerticalGroup
    -0.37
    ⋙
    -0.35
    /**
    -0.34
     Tick
    -0.33
     kasarigan
    -0.33
    ueuse
    -0.32
     pungkasnya
    -0.32
    Geplaatst
    -0.32
    undial
    -0.32
    gross
    -0.31
    POSITIVE LOGITS
     free
    1.69
     freedom
    1.44
    free
    1.41
    自由
    1.28
     liberty
    1.27
    Free
    1.23
     Free
    1.20
    freedom
    1.19
     libertad
    1.17
     libre
    1.16
    Act Density 0.103%

    No Known Activations