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

    Neuronpedia

    INDEX
    Explanations

    questions about economic or financial metrics

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

    Before a number with "let" or "calculate"

    np_acts-logits-general · gemini-2.0-flash

    exercises and problems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dolayı
    -0.48
    forKey
    -0.47
    Actualmente
    -0.44
     себя
    -0.44
    kloped
    -0.44
    aronne
    -0.44
     speech
    -0.43
    logique
    -0.43
     impacted
    -0.42
     ⁠
    -0.42
    POSITIVE LOGITS
     Exercise
    1.13
     Problem
    1.07
    Problem
    1.04
     exercise
    1.03
     problem
    1.01
    Exercise
    1.00
    exercise
    0.97
     Exercises
    0.94
     Problems
    0.93
    problem
    0.91
    Act Density 0.632%

    No Known Activations