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

    Neuronpedia

    INDEX
    Explanations

    Neat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     FIXME
    -0.07
     zkušen
    -0.07
     대통령
    -0.07
    .department
    -0.07
    .documents
    -0.07
     pollen
    -0.07
     forgiving
    -0.07
     Серг
    -0.07
     существ
    -0.07
    non
    -0.07
    POSITIVE LOGITS
     neat
    0.10
     tidy
    0.09
     neatly
    0.08
     duties
    0.07
     Neck
    0.07
     DY
    0.07
     dt
    0.07
     Clean
    0.06
     nan
    0.06
    repair
    0.06
    Act Density 0.003%

    No Known Activations