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

    Neuronpedia

    INDEX
    Explanations

    displayed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    density
    -0.93
     densities
    -0.93
    theless
    -0.91
     density
    -0.88
     Density
    -0.87
    ly
    -0.85
     denser
    -0.80
     depths
    -0.79
    Density
    -0.79
     utafitiHapana
    -0.78
    POSITIVE LOGITS
    newArrayList
    0.53
    Décès
    0.47
     cara
    0.44
     wir
    0.40
    yarnpkg
    0.40
    atrician
    0.39
    yor
    0.38
    stol
    0.37
    iomanip
    0.37
    archar
    0.36
    Act Density 0.072%

    No Known Activations