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

    Neuronpedia

    INDEX
    Explanations

    acrylic model, blue hour

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    matte
    0.40
    ඩි
    0.38
    "></
    0.38
     Arun
    0.37
    நிலையில்
    0.37
    マット
    0.36
     Reports
    0.35
    цкі
    0.35
     Unicorn
    0.34
    assign
    0.34
    POSITIVE LOGITS
     lineups
    0.42
     文化
    0.42
     ءِ
    0.41
     определяется
    0.40
     cultura
    0.39
     пле
    0.39
     ព
    0.39
     計算
    0.38
    пот
    0.38
     плюс
    0.38
    Act Density 0.001%

    No Known Activations