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

    Neuronpedia

    INDEX
    Explanations

    making adjustments to parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bukti
    0.78
     बनेंगे
    0.77
     infrastructures
    0.75
     voraus
    0.75
     accusing
    0.75
     инфраструк
    0.75
     reunite
    0.75
     consignment
    0.74
     कांड
    0.74
     reunion
    0.73
    POSITIVE LOGITS
     adjustable
    2.35
     adjusting
    2.19
    调节
    2.06
     tweaking
    2.06
     adjustment
    2.03
    调整
    2.03
    adjustable
    2.00
     Adjustable
    2.00
    調整
    2.00
     adjustments
    1.98
    Act Density 0.820%

    No Known Activations