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

    Neuronpedia

    INDEX
    Explanations

    musical notations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Intervention
    -0.09
     Emergency
    -0.08
     Kr
    -0.08
     Lowell
    -0.08
     Economist
    -0.08
     raven
    -0.08
     Guillermo
    -0.08
     Fitzgerald
    -0.08
     Dominicana
    -0.08
     corticost
    -0.07
    POSITIVE LOGITS
     prerequisites
    0.09
     pumping
    0.08
    .repo
    0.07
     natu
    0.07
     서
    0.07
     풀
    0.07
     anf
    0.07
    Worth
    0.07
    Filtering
    0.07
    ag
    0.07
    Act Density 0.001%

    No Known Activations