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

    Neuronpedia

    INDEX
    Explanations

    calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ٣
    -0.07
     biomass
    -0.07
    -ro
    -0.07
    ्रमण
    -0.07
     gs
    -0.07
     Ada
    -0.06
    Hel
    -0.06
    센
    -0.06
    adin
    -0.06
    .ef
    -0.06
    POSITIVE LOGITS
     calculations
    0.08
     сви
    0.07
     Design
    0.07
     simulated
    0.07
     calculation
    0.07
     calculated
    0.07
     simulation
    0.06
    ICollection
    0.06
     Commit
    0.06
     bureau
    0.06
    Act Density 0.024%

    No Known Activations