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

    Neuronpedia

    INDEX
    Explanations

    test

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Duterte
    -0.08
    丨
    -0.08
    .register
    -0.07
     Abdel
    -0.07
     hann
    -0.07
    ana
    -0.07
    á
    -0.07
     Band
    -0.07
     Sets
    -0.07
    .menu
    -0.07
    POSITIVE LOGITS
    してきた
    0.07
    /qt
    0.07
     пу
    0.07
     практич
    0.07
    てしま
    0.07
     vít
    0.06
     wil
    0.06
    fstream
    0.06
    حط
    0.06
    0.06
    Act Density 0.108%

    No Known Activations