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

    Neuronpedia

    INDEX
    Explanations

    short

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Laz
    -0.08
     laz
    -0.07
     Layer
    -0.07
    eder
    -0.07
    >*
    -0.06
    Li
    -0.06
     lø
    -0.06
     evaluating
    -0.06
     zug
    -0.06
    laz
    -0.06
    POSITIVE LOGITS
     short
    0.14
     Short
    0.13
    short
    0.11
     SHORT
    0.10
    Short
    0.10
     shorter
    0.08
     brief
    0.08
    .short
    0.08
    -short
    0.08
     Shorts
    0.08
    Act Density 0.033%

    No Known Activations