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

    Neuronpedia

    INDEX
    Explanations

    coordinates and drawing shapes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hostility
    -0.08
    (cipher
    -0.08
    \x
    -0.08
     glean
    -0.07
    (currency
    -0.07
    及时
    -0.07
     supplements
    -0.07
     Rules
    -0.07
     currency
    -0.07
    Rules
    -0.07
    POSITIVE LOGITS
     vertices
    0.08
    Vertices
    0.08
     visible
    0.08
     visibles
    0.08
    legd
    0.08
    _visible
    0.08
    řejmě
    0.08
    -visible
    0.08
     Visible
    0.08
     plotted
    0.08
    Act Density 0.033%

    No Known Activations