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

    Neuronpedia

    INDEX
    Explanations

    actions or processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ěné
    0.48
    اہم
    0.48
    न्ना
    0.46
    枨
    0.46
    évő
    0.45
    acées
    0.44
    ológicas
    0.44
    态
    0.43
     když
    0.43
     polymorphisms
    0.43
    POSITIVE LOGITS
     bertujuan
    0.54
     сюда
    0.52
     would
    0.52
    依頼
    0.49
     pretende
    0.49
     might
    0.48
    वाडी
    0.48
     делается
    0.48
     sarebbe
    0.48
     intends
    0.47
    Act Density 0.008%

    No Known Activations