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

    Neuronpedia

    INDEX
    Explanations

    they make up everything

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dukkham
    0.42
    າ
    0.39
    ځ
    0.37
    vida
    0.37
     มาก
    0.34
     לע
    0.34
     सि
    0.33
     tenaga
    0.33
    ंजी
    0.33
    ̣c
    0.32
    POSITIVE LOGITS
     qc
    0.36
     Critique
    0.36
     outpatient
    0.35
    codetest
    0.35
     QPushButton
    0.35
     Initial
    0.34
     Customize
    0.33
     deuxième
    0.33
     അവസാന
    0.33
    ২৩
    0.33
    Act Density 0.002%

    No Known Activations