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

    Neuronpedia

    INDEX
    Explanations

    Scalability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     products
    0.69
     produtos
    0.69
     product
    0.68
     продуктов
    0.68
    产品
    0.67
     missions
    0.64
     productos
    0.63
     Products
    0.63
     reception
    0.62
    製品
    0.62
    POSITIVE LOGITS
    icorn
    0.64
     Mene
    0.61
    NIR
    0.61
     Clone
    0.60
     Butcher
    0.60
    dou
    0.59
    iga
    0.57
    эф
    0.57
    Self
    0.57
    irsi
    0.56
    Act Density 0.134%

    No Known Activations