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

    Neuronpedia

    INDEX
    Explanations

    primary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    鸟
    -0.07
    isen
    -0.07
     Evidence
    -0.06
     behavior
    -0.06
    visit
    -0.06
     Behavior
    -0.06
    \d
    -0.06
     film
    -0.06
     filthy
    -0.06
     plaisir
    -0.06
    POSITIVE LOGITS
    	bytes
    0.07
     لأ
    0.07
    YNAM
    0.06
     meticulously
    0.06
     Mueller
    0.06
    累
    0.06
     dataSize
    0.06
    RY
    0.06
     Alger
    0.06
    .ItemStack
    0.06
    Act Density 0.002%

    No Known Activations