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

    Neuronpedia

    INDEX
    Explanations

    references to memories and past experiences

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

    recounting past experiences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -0.49
    addGap
    -0.40
    makeConstraints
    -0.39
     detailsNormal
    -0.39
     directs
    -0.39
    Segue
    -0.38
     végétal
    -0.38
     aussieht
    -0.37
     Domes
    -0.37
     deem
    -0.36
    POSITIVE LOGITS
    ########.
    0.58
    tagext
    0.50
     AssemblyCulture
    0.42
     aquella
    0.42
    ↹
    0.40
    ViewImports
    0.40
     pernah
    0.39
     aquel
    0.39
    ydney
    0.39
     past
    0.38
    Act Density 0.052%

    No Known Activations