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

    Neuronpedia

    INDEX
    Explanations

    completion or example

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    более
    0.45
     पर्सनल
    0.43
     INVESTMENT
    0.42
    FormParams
    0.41
    вершена
    0.41
    enquête
    0.41
    щите
    0.40
    수한
    0.40
    情报
    0.40
     PERSONAL
    0.40
    POSITIVE LOGITS
     havia
    0.47
     axis
    0.45
     met
    0.41
     Hayes
    0.41
     bathtub
    0.41
     clor
    0.40
     rigidity
    0.40
     cleaning
    0.40
     rigid
    0.40
     battery
    0.39
    Act Density 0.001%

    No Known Activations