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

    Neuronpedia

    INDEX
    Explanations

    Test

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bri
    -0.08
    탄
    -0.08
     emotions
    -0.07
    Lower
    -0.07
     pore
    -0.07
    就业
    -0.07
    hashtags
    -0.07
     tile
    -0.07
     scents
    -0.07
     fragrant
    -0.07
    POSITIVE LOGITS
     самых
    0.09
     antics
    0.09
     amplified
    0.08
     quello
    0.08
     provoc
    0.08
     बिल्कुल
    0.08
     amplification
    0.08
     taas
    0.08
     voyages
    0.07
    ుడు
    0.07
    Act Density 0.001%

    No Known Activations