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

    Neuronpedia

    INDEX
    Explanations

    ray

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    “To
    -0.07
    毕
    -0.07
    .reject
    -0.07
    iological
    -0.07
    因果
    -0.07
    (Level
    -0.06
    索取
    -0.06
    Directions
    -0.06
    MBOL
    -0.06
     Mixed
    -0.06
    POSITIVE LOGITS
    EEDED
    0.07
    	check
    0.07
     traff
    0.07
    วาง
    0.07
     GMO
    0.07
    祛斑
    0.07
    עות
    0.07
    étranger
    0.07
     pesticide
    0.07
     RO
    0.06
    Act Density 0.005%

    No Known Activations