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

    Neuronpedia

    INDEX
    Explanations

    Perform regression analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estimator
    0.87
     estimators
    0.81
     estimates
    0.81
     estimate
    0.79
     average
    0.78
    sums
    0.78
    avg
    0.76
     平均
    0.76
     Estimate
    0.75
     standardized
    0.74
    POSITIVE LOGITS
     subgroup
    1.00
     Receiver
    0.97
     receiver
    0.92
    Receiver
    0.87
     sensitivity
    0.85
     Sensitivity
    0.85
     суб
    0.84
    sensitivity
    0.82
    receiver
    0.82
    サブ
    0.79
    Act Density 0.005%

    No Known Activations