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

    Neuronpedia

    INDEX
    Explanations

    highly recommend or detailed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Gave
    0.45
     쭉
    0.41
     ढ
    0.40
     நா
    0.38
    広い
    0.38
     खूप
    0.38
     largo
    0.37
    }{}
    0.37
    shares
    0.37
    高的
    0.37
    POSITIVE LOGITS
     Highly
    0.48
    Highly
    0.48
     criticized
    0.47
    highly
    0.47
    děpodob
    0.47
     highly
    0.46
     publicized
    0.46
     likely
    0.45
     commended
    0.45
     commendable
    0.45
    Act Density 0.006%

    No Known Activations