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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DISABLE
    -0.06
    Σ
    -0.06
    hledem
    -0.06
    Government
    -0.06
     perspective
    -0.06
    "\
    -0.06
    аті
    -0.06
    ckt
    -0.06
    clusters
    -0.06
    ";//
    -0.06
    POSITIVE LOGITS
    arking
    0.07
     Runs
    0.07
     resemblance
    0.07
     indexed
    0.07
     Execute
    0.07
     mindfulness
    0.06
     Fortress
    0.06
     rt
    0.06
    Wrapper
    0.06
     je
    0.06
    Act Density 0.005%

    No Known Activations