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

    Neuronpedia

    INDEX
    Explanations

    physical components and specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     los
    0.49
     iguales
    0.47
     binh
    0.46
     iguais
    0.45
     antibiotics
    0.44
     extermin
    0.44
     alkaloids
    0.44
     horses
    0.44
     herbs
    0.44
     گھ
    0.44
    POSITIVE LOGITS
    0.47
    зона
    0.45
    权
    0.45
    试图
    0.43
    单个
    0.43
    唯一
    0.42
    抚
    0.41
    璋
    0.41
    棪
    0.40
    Layer
    0.40
    Act Density 0.011%

    No Known Activations