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

    Neuronpedia

    INDEX
    Explanations

    shadow

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     startup
    -0.08
    @Rest
    -0.08
     команд
    -0.08
    正文
    -0.08
     startups
    -0.08
     pren
    -0.08
    delimiter
    -0.08
     repl
    -0.08
     delimiter
    -0.08
    船
    -0.07
    POSITIVE LOGITS
     fundos
    0.09
     earrings
    0.09
     ರಿಂದ
    0.09
     Earrings
    0.09
     donkere
    0.08
     ores
    0.08
     fondos
    0.08
     AMOLED
    0.08
     оттен
    0.08
     THEM
    0.08
    Act Density 0.005%

    No Known Activations