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

    Neuronpedia

    INDEX
    Explanations

    'label:' definition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     роста
    1.86
    𝑔
    1.81
    ፈላጊ
    1.76
    𝑑
    1.76
     notValid
    1.70
    getType
    1.70
     danych
    1.66
     dej
    1.63
    𝑅
    1.60
     jsonData
    1.60
    POSITIVE LOGITS
    ي
    1.98
    ش
    1.73
    नि
    1.56
    т
    1.49
    c
    1.48
    y
    1.41
    ko
    1.40
    <bos>
    1.40
    ف
    1.38
    দেখ
    1.38
    Act Density 0.014%

    No Known Activations