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

    Neuronpedia

    INDEX
    Explanations

    Trom

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     financier
    -0.07
    Files
    -0.06
     способом
    -0.06
     symbolic
    -0.06
    .UUID
    -0.06
     музы
    -0.06
     Britain
    -0.06
    Hair
    -0.06
    Pie
    -0.06
     documentos
    -0.06
    POSITIVE LOGITS
    การแข
    0.08
     Trot
    0.08
    preh
    0.08
    )!=
    0.07
     รอบ
    0.07
    Metro
    0.07
    ()!=
    0.07
    .Throws
    0.06
    taking
    0.06
    .'));↵
    0.06
    Act Density 0.007%

    No Known Activations