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

    Neuronpedia

    INDEX
    Explanations

    astrology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     സാമൂഹ
    -0.09
     prompting
    -0.09
     최신
    -0.08
    <|startoftext|>
    -0.08
     вдох
    -0.08
     yap
    -0.08
     tqdm
    -0.08
     inspiring
    -0.08
     सामाजिक
    -0.07
     സോഷ്യ
    -0.07
    POSITIVE LOGITS
     unfavorable
    0.10
     favorable
    0.09
     besonderes
    0.09
     dign
    0.09
    0.08
     detrimental
    0.08
    avorable
    0.08
     اللاعب
    0.08
     iyi
    0.08
    _good
    0.08
    Act Density 0.009%
    No Known Activations