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

    Neuronpedia

    INDEX
    Explanations

    Detection limits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     flap
    -0.09
     quilting
    -0.08
     flop
    -0.08
     biome
    -0.08
    roof
    -0.08
     cál
    -0.08
     somet
    -0.08
    ledge
    -0.08
     taller
    -0.07
    bolt
    -0.07
    POSITIVE LOGITS
     concentrations
    0.11
     concentration
    0.09
     viral
    0.09
     serum
    0.08
     concentración
    0.08
     Viral
    0.08
     Konzentr
    0.08
     концентра
    0.08
    vatore
    0.08
    浓
    0.08
    Act Density 0.004%

    No Known Activations