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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ការពារ
    0.50
     CPUs
    0.48
    AOrdenar
    0.48
     meals
    0.47
     binaries
    0.46
    মিনা
    0.45
     😍
    0.45
     Dishes
    0.45
     comidas
    0.44
    ជំងឺ
    0.44
    POSITIVE LOGITS
    ANG
    0.45
    ider
    0.44
    án
    0.43
    angi
    0.43
    COST
    0.42
    ét
    0.42
    ash
    0.41
    icke
    0.41
    ๕
    0.41
     world
    0.40
    Act Density 0.005%

    No Known Activations