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

    Neuronpedia

    INDEX
    Explanations

    treated

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gaussian
    -0.07
    agon
    -0.07
     życ
    -0.06
    emplate
    -0.06
     Somehow
    -0.06
    NGC
    -0.06
    ILLE
    -0.06
    AGON
    -0.06
     coastline
    -0.06
     Simpson
    -0.06
    POSITIVE LOGITS
     treated
    0.13
     treats
    0.11
     treatment
    0.11
     treat
    0.10
     treating
    0.09
     Treat
    0.09
    -treated
    0.09
    扱
    0.09
     tratamiento
    0.08
     Tre
    0.08
    Act Density 0.025%

    No Known Activations