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

    Neuronpedia

    INDEX
    Explanations

    Here are details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     birkaç
    0.83
     several
    0.80
     кілька
    0.80
     várias
    0.79
    いくつかの
    0.77
     několik
    0.77
     몇
    0.76
     flera
    0.76
    Several
    0.75
    several
    0.75
    POSITIVE LOGITS
    Описание
    0.44
    setDescription
    0.41
     Hai
    0.41
     Descriptions
    0.41
    解説
    0.40
     Details
    0.40
     brief
    0.39
     descriptions
    0.38
     статья
    0.38
     explan
    0.38
    Act Density 0.053%

    No Known Activations