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

    Neuronpedia

    INDEX
    Explanations

    variability indicators or statistical measures of uncertainty in data

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

    mean ± standard deviation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enfans
    -0.66
     avoient
    -0.58
     étoient
    -0.51
     college
    -0.51
     Murillo
    -0.51
    ூர்
    -0.48
     Defensa
    -0.47
    ️⃣
    -0.46
     kids
    -0.46
    college
    -0.46
    POSITIVE LOGITS
     ±
    1.92
    ±
    1.66
     (±
    1.38
     ± 
    0.96
    ∓
    0.77
     +-
    0.75
    ± 
    0.73
     ^=
    0.71
     +/-
    0.70
    0.70
    Act Density 0.026%

    No Known Activations