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

    Neuronpedia

    INDEX
    Explanations

    references to studies or research papers

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

    study aims and goals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ьажоргаш
    -0.49
    rosin
    -0.47
    цездатний
    -0.46
     ब्रेकडाउन
    -0.45
    ))))))))
    -0.45
    conuts
    -0.45
     propOrder
    -0.44
    ogs
    -0.44
    ftagPool
    -0.43
     }))
    -0.42
    POSITIVE LOGITS
     aim
    0.52
    StoryboardSegue
    0.52
     objetivo
    0.48
     aims
    0.46
     aiming
    0.45
    èdia
    0.44
    Aim
    0.44
     cél
    0.42
     goal
    0.42
     يتيمه
    0.41
    Act Density 0.073%

    No Known Activations