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

    Neuronpedia

    INDEX
    Explanations

    minimization

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [color
    -0.10
    [column
    -0.09
    [channel
    -0.09
    .astype
    -0.09
     magie
    -0.08
     qualifiers
    -0.08
     redo
    -0.08
    Ansi
    -0.08
    }"↵
    -0.08
     tonumber
    -0.08
    POSITIVE LOGITS
     minimizing
    0.11
     minim
    0.11
     optimal
    0.11
    optimal
    0.11
     convex
    0.11
    Optimal
    0.10
     Optimal
    0.10
     minimized
    0.10
     minimizes
    0.09
     minimize
    0.09
    Act Density 0.010%

    No Known Activations