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

    Neuronpedia

    INDEX
    Explanations

    Proper nouns and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    おく
    0.57
     produksi
    0.53
    𝔬
    0.50
    วัสดี
    0.46
    ittää
    0.46
    𝔦
    0.46
     representar
    0.45
     parametrization
    0.45
     représentation
    0.45
     grabación
    0.45
    POSITIVE LOGITS
     Αν
    0.49
     Ан
    0.46
    fang
    0.45
     дам
    0.45
    жды
    0.45
    穷
    0.44
    번호
    0.42
    并通过
    0.42
    尃
    0.41
    irin
    0.41
    Act Density 0.001%

    No Known Activations