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

    Neuronpedia

    INDEX
    Explanations

    postfix

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Th
    -0.06
    より
    -0.06
    國
    -0.06
     calves
    -0.06
    According
    -0.06
     точно
    -0.06
    -0.06
     Bazı
    -0.06
    Opaque
    -0.06
    -born
    -0.06
    POSITIVE LOGITS
     sonic
    0.07
     Mat
    0.06
    unsqueeze
    0.06
     Gest
    0.06
     subsid
    0.06
     Gab
    0.06
    .Feed
    0.06
    .Load
    0.06
     приклад
    0.06
    brane
    0.06
    Act Density 0.012%

    No Known Activations