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

    Neuronpedia

    INDEX
    Explanations

    contracts and renewals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kcal
    -0.09
     voel
    -0.08
     Feel
    -0.08
     Calories
    -0.08
     collega
    -0.08
    ർന്ന്
    -0.08
     jeans
    -0.08
     épr
    -0.08
     strangers
    -0.08
     oxy
    -0.08
    POSITIVE LOGITS
     своев
    0.09
     correctly
    0.09
     renewal
    0.08
     carefully
    0.08
     vigilance
    0.08
     vigilant
    0.08
     properly
    0.08
    -
    0.08
     timely
    0.08
    Renew
    0.08
    Act Density 0.051%

    No Known Activations