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

    Neuronpedia

    INDEX
    Explanations

    specific scientific terms and metrics in a technical context

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

    occafion, poffible, anchor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.42
     kaynağından
    -0.38
    Przypisy
    -0.38
    Bronnen
    -0.38
    хьтан
    -0.35
    mal
    -0.35
     برانيه
    -0.34
    ofollow
    -0.34
     للاسماء
    -0.33
    cree
    -0.33
    POSITIVE LOGITS
    0.68
     occafion
    0.62
    UnusedPrivate
    0.61
     occaf
    0.60
     poffe
    0.56
    
    0.54
     raiſ
    0.53
     poffible
    0.51
     fubject
    0.51
    setVerticalGroup
    0.51
    Act Density 0.066%

    No Known Activations