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

    Neuronpedia

    INDEX
    Explanations

    Math/logical problem

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     
    -0.09
     Doom
    -0.07
     निर्माण
    -0.07
    -0.07
     paleo
    -0.07
     pł
    -0.07
     cu
    -0.07
     
    -0.07
    Few
    -0.07
     �
    -0.07
    POSITIVE LOGITS
     Gé
    0.08
     folder
    0.08
     랜
    0.08
    ibri
    0.08
    .IS
    0.08
     secretary
    0.08
    .IB
    0.08
    iciência
    0.08
    .PR
    0.08
    Etiqueta
    0.07
    Act Density 0.069%
    No Known Activations