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

    Neuronpedia

    INDEX
    Explanations

    categorize and divide

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     olabilir
    0.50
     potrebbero
    0.45
     potrebbe
    0.41
     Would
    0.41
     pourraient
    0.40
     pourrait
    0.40
     benötigt
    0.40
     dimost
    0.40
    教程
    0.40
     könnte
    0.40
    POSITIVE LOGITS
    categor
    0.70
     podziel
    0.67
     try
    0.65
     divided
    0.64
     categorize
    0.63
     categor
    0.63
     tries
    0.63
    แบ่ง
    0.63
     divide
    0.62
    divided
    0.62
    Act Density 0.001%

    No Known Activations