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

    Neuronpedia

    INDEX
    Explanations

    density

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Obt
    -0.07
     stepping
    -0.07
    Steps
    -0.07
    Step
    -0.07
    stav
    -0.07
    702
    -0.07
     campaigning
    -0.06
     выступ
    -0.06
    swer
    -0.06
     blurred
    -0.06
    POSITIVE LOGITS
    Density
    0.09
     density
    0.08
    density
    0.08
     Density
    0.07
    ęż
    0.07
    Α
    0.07
    actories
    0.07
     densities
    0.06
    ens
    0.06
    dens
    0.06
    Act Density 0.011%

    No Known Activations