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

    Neuronpedia

    INDEX
    Explanations

    keys in structured data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    例文帳に追加
    0.40
    紝
    0.40
    ብስብ
    0.38
    NuGet
    0.37
    DISCUSSION
    0.35
     आला
    0.35
    нија
    0.35
    രാണ്
    0.35
    बेल
    0.33
    ەڵ
    0.33
    POSITIVE LOGITS
    :
    1.14
     :
    0.92
    ':
    0.84
    :'
    0.81
    :""
    0.80
    :"
    0.79
    ：
    0.79
    :{
    0.77
    :["
    0.77
    :',
    0.75
    Act Density 0.025%

    No Known Activations