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

    Neuronpedia

    INDEX
    Explanations

    future value prediction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Qualified
    0.49
    Punjab
    0.46
    ൺലൈ
    0.43
    Young
    0.42
    ffic
    0.41
     gama
    0.41
    Mum
    0.40
    Autumn
    0.40
    Salt
    0.39
     iba
    0.38
    POSITIVE LOGITS
     endpoints
    0.56
     forecasting
    0.56
     outcome
    0.55
     outcomes
    0.54
     predictors
    0.54
     Outcomes
    0.52
     Outcome
    0.51
     predictions
    0.48
     forecasted
    0.46
     omissions
    0.46
    Act Density 0.002%

    No Known Activations