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

    Neuronpedia

    INDEX
    Explanations

    empirical formula calculation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    amut
    -0.07
    °C
    -0.07
    aste
    -0.07
     Arb
    -0.07
     Mutation
    -0.07
     microbial
    -0.07
    (binding
    -0.07
     μ
    -0.07
     ();
↵
    -0.07
     nhiều
    -0.07
    POSITIVE LOGITS
     criminals
    0.08
     eleição
    0.08
     elet
    0.08
     aansprak
    0.08
     gevolgen
    0.08
    zinha
    0.08
     rou
    0.08
     nouv
    0.08
     objectively
    0.08
     foram
    0.08
    Act Density 0.003%

    No Known Activations