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

    Neuronpedia

    INDEX
    Explanations

    alexa commands and code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     optimal
    0.73
     tech
    0.71
    నూ
    0.70
     gest
    0.70
    ic
    0.70
    ان
    0.69
     additional
    0.69
    ely
    0.69
    ilage
    0.69
    ley
    0.68
    POSITIVE LOGITS
    Diện
    1.09
    aksud
    0.97
    ツイ
    0.94
    Denote
    0.92
    یعنی
    0.90
    Translatef
    0.90
    Identify
    0.89
     Means
    0.89
     જિલ્લા
    0.88
    Está
    0.88
    Act Density 0.147%

    No Known Activations