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

    Neuronpedia

    INDEX
    Explanations

    terms related to releasing or freeing entities from confinement

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

    release or unleash

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resourceCulture
    -0.57
    RenderAtEndOf
    -0.56
     pinulongan
    -0.47
     Lightboxes
    -0.46
    xase
    -0.46
    Produzione
    -0.45
    ImageContext
    -0.45
    IsMutable
    -0.43
     artikkelen
    -0.42
    PostInfinity
    -0.41
    POSITIVE LOGITS
     freed
    0.51
     release
    0.51
     unleash
    0.49
     escaped
    0.47
     unlocked
    0.46
     released
    0.46
     unleashed
    0.46
     releases
    0.46
     releasing
    0.46
    UNLOCK
    0.45
    Act Density 0.193%

    No Known Activations